Upload 33 files

.gitattributes

@@ -1,37 +1,31 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-master_tmp.png filter=lfs diff=lfs merge=lfs -text
-to_score_planogram_tmp.png filter=lfs diff=lfs merge=lfs -text
+sample_master_planogram.jpeg filter=lfs diff=lfs merge=lfs -text
+tmp.png filter=lfs diff=lfs merge=lfs -text
+tmp/master_tmp.png filter=lfs diff=lfs merge=lfs -text
+tmp/to_score_planogram_tmp.png filter=lfs diff=lfs merge=lfs -text

CONTRIBUTING.md

@@ -0,0 +1,94 @@
+## Contributing to YOLOv5 🚀
+
+We love your input! We want to make contributing to YOLOv5 as easy and transparent as possible, whether it's:
+
+- Reporting a bug
+- Discussing the current state of the code
+- Submitting a fix
+- Proposing a new feature
+- Becoming a maintainer
+
+YOLOv5 works so well due to our combined community effort, and for every small improvement you contribute you will be
+helping push the frontiers of what's possible in AI 😃!
+
+## Submitting a Pull Request (PR) 🛠️
+
+Submitting a PR is easy! This example shows how to submit a PR for updating `requirements.txt` in 4 steps:
+
+### 1. Select File to Update
+
+Select `requirements.txt` to update by clicking on it in GitHub.
+<p align="center"><img width="800" alt="PR_step1" src="https://user-images.githubusercontent.com/26833433/122260847-08be2600-ced4-11eb-828b-8287ace4136c.png"></p>
+
+### 2. Click 'Edit this file'
+
+Button is in top-right corner.
+<p align="center"><img width="800" alt="PR_step2" src="https://user-images.githubusercontent.com/26833433/122260844-06f46280-ced4-11eb-9eec-b8a24be519ca.png"></p>
+
+### 3. Make Changes
+
+Change `matplotlib` version from `3.2.2` to `3.3`.
+<p align="center"><img width="800" alt="PR_step3" src="https://user-images.githubusercontent.com/26833433/122260853-0a87e980-ced4-11eb-9fd2-3650fb6e0842.png"></p>
+
+### 4. Preview Changes and Submit PR
+
+Click on the **Preview changes** tab to verify your updates. At the bottom of the screen select 'Create a **new branch**
+for this commit', assign your branch a descriptive name such as `fix/matplotlib_version` and click the green **Propose
+changes** button. All done, your PR is now submitted to YOLOv5 for review and approval 😃!
+<p align="center"><img width="800" alt="PR_step4" src="https://user-images.githubusercontent.com/26833433/122260856-0b208000-ced4-11eb-8e8e-77b6151cbcc3.png"></p>
+
+### PR recommendations
+
+To allow your work to be integrated as seamlessly as possible, we advise you to:
+
+- ✅ Verify your PR is **up-to-date with origin/master.** If your PR is behind origin/master an
+  automatic [GitHub actions](https://github.com/ultralytics/yolov5/blob/master/.github/workflows/rebase.yml) rebase may
+  be attempted by including the /rebase command in a comment body, or by running the following code, replacing 'feature'
+  with the name of your local branch:
+
+```bash
+git remote add upstream https://github.com/ultralytics/yolov5.git
+git fetch upstream
+git checkout feature  # <----- replace 'feature' with local branch name
+git merge upstream/master
+git push -u origin -f
+```
+
+- ✅ Verify all Continuous Integration (CI) **checks are passing**.
+- ✅ Reduce changes to the absolute **minimum** required for your bug fix or feature addition. _"It is not daily increase
+  but daily decrease, hack away the unessential. The closer to the source, the less wastage there is."_  -Bruce Lee
+
+## Submitting a Bug Report 🐛
+
+If you spot a problem with YOLOv5 please submit a Bug Report!
+
+For us to start investigating a possibel problem we need to be able to reproduce it ourselves first. We've created a few
+short guidelines below to help users provide what we need in order to get started.
+
+When asking a question, people will be better able to provide help if you provide **code** that they can easily
+understand and use to **reproduce** the problem. This is referred to by community members as creating
+a [minimum reproducible example](https://stackoverflow.com/help/minimal-reproducible-example). Your code that reproduces
+the problem should be:
+
+* ✅ **Minimal** – Use as little code as possible that still produces the same problem
+* ✅ **Complete** – Provide **all** parts someone else needs to reproduce your problem in the question itself
+* ✅ **Reproducible** – Test the code you're about to provide to make sure it reproduces the problem
+
+In addition to the above requirements, for [Ultralytics](https://ultralytics.com/) to provide assistance your code
+should be:
+
+* ✅ **Current** – Verify that your code is up-to-date with current
+  GitHub [master](https://github.com/ultralytics/yolov5/tree/master), and if necessary `git pull` or `git clone` a new
+  copy to ensure your problem has not already been resolved by previous commits.
+* ✅ **Unmodified** – Your problem must be reproducible without any modifications to the codebase in this
+  repository. [Ultralytics](https://ultralytics.com/) does not provide support for custom code ⚠️.
+
+If you believe your problem meets all of the above criteria, please close this issue and raise a new one using the 🐛 **
+Bug Report** [template](https://github.com/ultralytics/yolov5/issues/new/choose) and providing
+a [minimum reproducible example](https://stackoverflow.com/help/minimal-reproducible-example) to help us better
+understand and diagnose your problem.
+
+## License
+
+By contributing, you agree that your contributions will be licensed under
+the [GPL-3.0 license](https://choosealicense.com/licenses/gpl-3.0/)

Dockerfile

@@ -0,0 +1,60 @@
+# # YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# # Start FROM Nvidia PyTorch image https://ngc.nvidia.com/catalog/containers/nvidia:pytorch
+# FROM nvcr.io/nvidia/pytorch:21.05-py3
+
+# # Install linux packages
+# RUN apt update && apt install -y zip htop screen libgl1-mesa-glx
+
+# # Install python dependencies
+# COPY requirements.txt .
+# RUN python -m pip install --upgrade pip
+# RUN pip uninstall -y nvidia-tensorboard nvidia-tensorboard-plugin-dlprof
+# RUN pip install --no-cache -r requirements.txt coremltools onnx gsutil notebook
+# RUN pip install --no-cache -U torch torchvision numpy
+# # RUN pip install --no-cache torch==1.9.0+cu111 torchvision==0.10.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html
+
+# # Create working directory
+# RUN mkdir -p /usr/src/app
+# WORKDIR /usr/src/app
+
+# # Copy contents
+# COPY . /usr/src/app
+
+# # Set environment variables
+# ENV HOME=/usr/src/app
+
+
+# Usage Examples -------------------------------------------------------------------------------------------------------
+
+# Build and Push
+# t=ultralytics/yolov5:latest && sudo docker build -t $t . && sudo docker push $t
+
+# Pull and Run
+# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all $t
+
+# Pull and Run with local directory access
+# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/datasets:/usr/src/datasets $t
+
+# Kill all
+# sudo docker kill $(sudo docker ps -q)
+
+# Kill all image-based
+# sudo docker kill $(sudo docker ps -qa --filter ancestor=ultralytics/yolov5:latest)
+
+# Bash into running container
+# sudo docker exec -it 5a9b5863d93d bash
+
+# Bash into stopped container
+# id=$(sudo docker ps -qa) && sudo docker start $id && sudo docker exec -it $id bash
+
+# Clean up
+# docker system prune -a --volumes
+FROM python:3.9
+EXPOSE 8501
+WORKDIR /app
+COPY requirements.txt ./requirements.txt
+RUN pip3 install -r requirements.txt
+COPY . .
+# CMD streamlit run app.py
+CMD streamlit run --server.port $PORT app.py

LICENSE

@@ -0,0 +1,674 @@
+GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.  We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors.  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights.  Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received.  You must make sure that they, too, receive
+or can get the source code.  And you must show them these terms so they
+know their rights.
+
+  Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+  For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software.  For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+  Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so.  This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software.  The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable.  Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products.  If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+  Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary.  To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Use with the GNU Affero General Public License.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+    <program>  Copyright (C) <year>  <name of author>
+    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<http://www.gnu.org/licenses/>.
+
+  The GNU General Public License does not permit incorporating your program
+into proprietary programs.  If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.  But first, please read
+<http://www.gnu.org/philosophy/why-not-lgpl.html>.

Procfile

@@ -0,0 +1 @@
+web: sh setup.sh && streamlit run app.py

README.md

@@ -1,13 +1,166 @@
 ---
-title: Plano Lit
-emoji: 🚀
-colorFrom: purple
-colorTo: red
 sdk: streamlit
-sdk_version: 1.33.0
+sdk_version: 1.10.0 # The latest supported version
 app_file: app.py
 pinned: false
-license: apache-2.0
+fullWidth: True
 ---
+## <div align="center">Planogram Scoring</div>
+<p>
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+</p>
+- Train a Yolo Model on the available products in our data base to detect them on a shelf
+- https://wandb.ai/abhilash001vj/YOLOv5/runs/1v6yh7nk?workspace=user-abhilash001vj
+- Have the master planogram data captured as a matrix of products encoded as numbers (label encoding by looking the products names saved in a  list of all - the available product names )
+- Detect the products on real images from stores.
+- Arrange the detected products in the captured photograph to rows and columns 
+- Compare the product arrangement of captured photograph to the existing master planogram and produce the compliance score for correctly placed products
+
+</div>
+
+## <div align="center">YOLOv5</div>
+<p>
+YOLOv5 🚀 is a family of object detection architectures and models pretrained on the COCO dataset, and represents <a href="https://ultralytics.com">Ultralytics</a>
+ open-source research into future vision AI methods, incorporating lessons learned and best practices evolved over thousands of hours of research and development.
+</p>
+
+</div>
+
+## <div align="center">Documentation</div>
+
+See the [YOLOv5 Docs](https://docs.ultralytics.com) for full documentation on training, testing and deployment.
+
+## <div align="center">Quick Start Examples</div>
+
+<details open>
+<summary>Install</summary>
+
+[**Python>=3.6.0**](https://www.python.org/) is required with all
+[requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) installed including
+[**PyTorch>=1.7**](https://pytorch.org/get-started/locally/):
+<!-- $ sudo apt update && apt install -y libgl1-mesa-glx libsm6 libxext6 libxrender-dev -->
+
+```bash
+$ git clone https://github.com/ultralytics/yolov5
+$ cd yolov5
+$ pip install -r requirements.txt
+```
+
+</details>
+
+<details open>
+<summary>Inference</summary>
+
+Inference with YOLOv5 and [PyTorch Hub](https://github.com/ultralytics/yolov5/issues/36). Models automatically download
+from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases).
+
+```python
+import torch
+
+# Model
+model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # or yolov5m, yolov5l, yolov5x, custom
+
+# Images
+img = 'https://ultralytics.com/images/zidane.jpg'  # or file, Path, PIL, OpenCV, numpy, list
+
+# Inference
+results = model(img)
+
+# Results
+results.print()  # or .show(), .save(), .crop(), .pandas(), etc.
+```
+
+</details>
+
+
+## <div align="center">Why YOLOv5</div>
+
+<p align="center"><img width="800" src="https://user-images.githubusercontent.com/26833433/114313216-f0a5e100-9af5-11eb-8445-c682b60da2e3.png"></p>
+<details>
+  <summary>YOLOv5-P5 640 Figure (click to expand)</summary>
+
+<p align="center"><img width="800" src="https://user-images.githubusercontent.com/26833433/114313219-f1d70e00-9af5-11eb-9973-52b1f98d321a.png"></p>
+</details>
+<details>
+  <summary>Figure Notes (click to expand)</summary>
+
+* GPU Speed measures end-to-end time per image averaged over 5000 COCO val2017 images using a V100 GPU with batch size
+  32, and includes image preprocessing, PyTorch FP16 inference, postprocessing and NMS.
+* EfficientDet data from [google/automl](https://github.com/google/automl) at batch size 8.
+* **Reproduce** by
+  `python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt`
+
+</details>
+
+### Pretrained Checkpoints
+
+[assets]: https://github.com/ultralytics/yolov5/releases
+
+|Model |size<br><sup>(pixels) |mAP<sup>val<br>0.5:0.95 |mAP<sup>test<br>0.5:0.95 |mAP<sup>val<br>0.5 |Speed<br><sup>V100 (ms) | |params<br><sup>(M) |FLOPs<br><sup>640 (B)
+|---                    |---  |---      |---      |---      |---     |---|---   |---
+|[YOLOv5s][assets]      |640  |36.7     |36.7     |55.4     |**2.0** |   |7.3   |17.0
+|[YOLOv5m][assets]      |640  |44.5     |44.5     |63.1     |2.7     |   |21.4  |51.3
+|[YOLOv5l][assets]      |640  |48.2     |48.2     |66.9     |3.8     |   |47.0  |115.4
+|[YOLOv5x][assets]      |640  |**50.4** |**50.4** |**68.8** |6.1     |   |87.7  |218.8
+|                       |     |         |         |         |        |   |      |
+|[YOLOv5s6][assets]     |1280 |43.3     |43.3     |61.9     |**4.3** |   |12.7  |17.4
+|[YOLOv5m6][assets]     |1280 |50.5     |50.5     |68.7     |8.4     |   |35.9  |52.4
+|[YOLOv5l6][assets]     |1280 |53.4     |53.4     |71.1     |12.3    |   |77.2  |117.7
+|[YOLOv5x6][assets]     |1280 |**54.4** |**54.4** |**72.0** |22.4    |   |141.8 |222.9
+|                       |     |         |         |         |        |   |      |
+|[YOLOv5x6][assets] TTA |1280 |**55.0** |**55.0** |**72.0** |70.8    |   |-     |-
+
+<details>
+  <summary>Table Notes (click to expand)</summary>
+
+* AP<sup>test</sup> denotes COCO [test-dev2017](http://cocodataset.org/#upload) server results, all other AP results
+  denote val2017 accuracy.
+* AP values are for single-model single-scale unless otherwise noted. **Reproduce mAP**
+  by `python val.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65`
+* Speed<sub>GPU</sub> averaged over 5000 COCO val2017 images using a
+  GCP [n1-standard-16](https://cloud.google.com/compute/docs/machine-types#n1_standard_machine_types) V100 instance, and
+  includes FP16 inference, postprocessing and NMS. **Reproduce speed**
+  by `python val.py --data coco.yaml --img 640 --conf 0.25 --iou 0.45 --half`
+* All checkpoints are trained to 300 epochs with default settings and hyperparameters (no autoaugmentation).
+* Test Time Augmentation ([TTA](https://github.com/ultralytics/yolov5/issues/303)) includes reflection and scale
+  augmentation. **Reproduce TTA** by `python val.py --data coco.yaml --img 1536 --iou 0.7 --augment`
+
+</details>
+
+## <div align="center">Contribute</div>
+
+We love your input! We want to make contributing to YOLOv5 as easy and transparent as possible. Please see
+our [Contributing Guide](CONTRIBUTING.md) to get started.
+
+## <div align="center">Contact</div>
+
+For issues running YOLOv5 please visit [GitHub Issues](https://github.com/ultralytics/yolov5/issues). For business or
+professional support requests please visit [https://ultralytics.com/contact](https://ultralytics.com/contact).
+
+<br>
+
+<div align="center">
+    <a href="https://github.com/ultralytics">
+        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-github.png" width="3%"/>
+    </a>
+    <img width="3%" />
+    <a href="https://www.linkedin.com/company/ultralytics">
+        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-linkedin.png" width="3%"/>
+    </a>
+    <img width="3%" />
+    <a href="https://twitter.com/ultralytics">
+        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-twitter.png" width="3%"/>
+    </a>
+    <img width="3%" />
+    <a href="https://youtube.com/ultralytics">
+        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-youtube.png" width="3%"/>
+    </a>
+    <img width="3%" />
+    <a href="https://www.facebook.com/ultralytics">
+        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-facebook.png" width="3%"/>
+    </a>
+    <img width="3%" />
+    <a href="https://www.instagram.com/ultralytics/">
+        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-instagram.png" width="3%"/>
+    </a>
+</div>

_requirements.txt

@@ -0,0 +1,36 @@
+# pip install -r requirements.txt
+streamlit
+# base ----------------------------------------
+# matplotlib>=3.2.2
+numpy>=1.18.5
+# opencv-python>=4.1.2
+# http://download.pytorch.org/whl/cpu/torch-1.7.1%2Bcpu-cp39-cp39-linux_x86_64.whl
+# gunicorn == 19.9.0
+# torchvision==0.2.2
+opencv-python-headless>=4.1.2
+Pillow>=8.0.0
+PyYAML>=5.3.1
+scipy>=1.4.1
+torch>=1.7.0
+torchvision>=0.8.1
+tqdm>=4.41.0
+
+# logging -------------------------------------
+# tensorboard>=2.4.1
+# wandb
+
+# plotting ------------------------------------
+# seaborn>=0.11.0
+pandas
+
+# export --------------------------------------
+# coremltools>=4.1
+# onnx>=1.9.0
+# scikit-learn==0.19.2  # for coreml quantization
+# tensorflow==2.4.1  # for TFLite export
+
+# extras --------------------------------------
+# Cython  # for pycocotools https://github.com/cocodataset/cocoapi/issues/172
+# pycocotools>=2.0  # COCO mAP
+# albumentations>=1.0.3
+# thop  # FLOPs computation

detect.py

@@ -0,0 +1,460 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Run YOLOv5 detection inference on images, videos, directories, globs, YouTube, webcam, streams, etc.
+
+Usage - sources:
+    $ python detect.py --weights yolov5s.pt --source 0                               # webcam
+                                                     img.jpg                         # image
+                                                     vid.mp4                         # video
+                                                     screen                          # screenshot
+                                                     path/                           # directory
+                                                     list.txt                        # list of images
+                                                     list.streams                    # list of streams
+                                                     'path/*.jpg'                    # glob
+                                                     'https://youtu.be/Zgi9g1ksQHc'  # YouTube
+                                                     'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
+
+Usage - formats:
+    $ python detect.py --weights yolov5s.pt                 # PyTorch
+                                 yolov5s.torchscript        # TorchScript
+                                 yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
+                                 yolov5s_openvino_model     # OpenVINO
+                                 yolov5s.engine             # TensorRT
+                                 yolov5s.mlmodel            # CoreML (macOS-only)
+                                 yolov5s_saved_model        # TensorFlow SavedModel
+                                 yolov5s.pb                 # TensorFlow GraphDef
+                                 yolov5s.tflite             # TensorFlow Lite
+                                 yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
+                                 yolov5s_paddle_model       # PaddlePaddle
+"""
+
+import argparse
+import os
+import platform
+import sys
+from pathlib import Path
+
+import torch
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[0]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+from models.common import DetectMultiBackend
+from utils.dataloaders import (
+    IMG_FORMATS,
+    VID_FORMATS,
+    LoadImages,
+    LoadScreenshots,
+    LoadStreams,
+)
+from utils.general import (
+    LOGGER,
+    Profile,
+    check_file,
+    check_img_size,
+    check_imshow,
+    check_requirements,
+    colorstr,
+    cv2,
+    increment_path,
+    non_max_suppression,
+    print_args,
+    scale_boxes,
+    strip_optimizer,
+    xyxy2xywh,
+)
+from utils.plots import Annotator, colors, save_one_box
+from utils.torch_utils import select_device, smart_inference_mode
+
+
+@smart_inference_mode()
+def run(
+    weights=ROOT / "yolov5s.pt",  # model path or triton URL
+    source=ROOT / "data/images",  # file/dir/URL/glob/screen/0(webcam)
+    data=ROOT / "data/coco128.yaml",  # dataset.yaml path
+    imgsz=(640, 640),  # inference size (height, width)
+    conf_thres=0.25,  # confidence threshold
+    iou_thres=0.45,  # NMS IOU threshold
+    max_det=1000,  # maximum detections per image
+    device="",  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+    view_img=False,  # show results
+    save_txt=False,  # save results to *.txt
+    save_conf=False,  # save confidences in --save-txt labels
+    save_crop=False,  # save cropped prediction boxes
+    nosave=False,  # do not save images/videos
+    classes=None,  # filter by class: --class 0, or --class 0 2 3
+    agnostic_nms=False,  # class-agnostic NMS
+    augment=False,  # augmented inference
+    visualize=False,  # visualize features
+    update=False,  # update all models
+    project=ROOT / "runs/detect",  # save results to project/name
+    name="exp",  # save results to project/name
+    exist_ok=False,  # existing project/name ok, do not increment
+    line_thickness=3,  # bounding box thickness (pixels)
+    hide_labels=False,  # hide labels
+    hide_conf=False,  # hide confidences
+    half=False,  # use FP16 half-precision inference
+    dnn=False,  # use OpenCV DNN for ONNX inference
+    vid_stride=1,  # video frame-rate stride
+):
+    source = str(source)
+    save_img = not nosave and not source.endswith(
+        ".txt"
+    )  # save inference images
+    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
+    is_url = source.lower().startswith(
+        ("rtsp://", "rtmp://", "http://", "https://")
+    )
+    webcam = (
+        source.isnumeric()
+        or source.endswith(".streams")
+        or (is_url and not is_file)
+    )
+    screenshot = source.lower().startswith("screen")
+    if is_url and is_file:
+        source = check_file(source)  # download
+
+    # Directories
+    save_dir = increment_path(
+        Path(project) / name, exist_ok=exist_ok
+    )  # increment run
+    (save_dir / "labels" if save_txt else save_dir).mkdir(
+        parents=True, exist_ok=True
+    )  # make dir
+
+    # Load model
+    device = select_device(device)
+    model = DetectMultiBackend(
+        weights, device=device, dnn=dnn, data=data, fp16=half
+    )
+    stride, names, pt = model.stride, model.names, model.pt
+    imgsz = check_img_size(imgsz, s=stride)  # check image size
+
+    # Dataloader
+    bs = 1  # batch_size
+    if webcam:
+        view_img = check_imshow(warn=True)
+        dataset = LoadStreams(
+            source,
+            img_size=imgsz,
+            stride=stride,
+            auto=pt,
+            vid_stride=vid_stride,
+        )
+        bs = len(dataset)
+    elif screenshot:
+        dataset = LoadScreenshots(
+            source, img_size=imgsz, stride=stride, auto=pt
+        )
+    else:
+        dataset = LoadImages(
+            source,
+            img_size=imgsz,
+            stride=stride,
+            auto=pt,
+            vid_stride=vid_stride,
+        )
+    vid_path, vid_writer = [None] * bs, [None] * bs
+
+    # Run inference
+    model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz))  # warmup
+    seen, windows, dt = 0, [], (Profile(), Profile(), Profile())
+    for path, im, im0s, vid_cap, s in dataset:
+        with dt[0]:
+            im = torch.from_numpy(im).to(model.device)
+            im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
+            im /= 255  # 0 - 255 to 0.0 - 1.0
+            if len(im.shape) == 3:
+                im = im[None]  # expand for batch dim
+
+        # Inference
+        with dt[1]:
+            visualize = (
+                increment_path(save_dir / Path(path).stem, mkdir=True)
+                if visualize
+                else False
+            )
+            pred = model(im, augment=augment, visualize=visualize)
+
+        # NMS
+        with dt[2]:
+            pred = non_max_suppression(
+                pred,
+                conf_thres,
+                iou_thres,
+                classes,
+                agnostic_nms,
+                max_det=max_det,
+            )
+
+        # Second-stage classifier (optional)
+        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
+
+        # Process predictions
+        for i, det in enumerate(pred):  # per image
+            seen += 1
+            if webcam:  # batch_size >= 1
+                p, im0, frame = path[i], im0s[i].copy(), dataset.count
+                s += f"{i}: "
+            else:
+                p, im0, frame = path, im0s.copy(), getattr(dataset, "frame", 0)
+
+            p = Path(p)  # to Path
+            save_path = str(save_dir / p.name)  # im.jpg
+            txt_path = str(save_dir / "labels" / p.stem) + (
+                "" if dataset.mode == "image" else f"_{frame}"
+            )  # im.txt
+            s += "%gx%g " % im.shape[2:]  # print string
+            gn = torch.tensor(im0.shape)[
+                [1, 0, 1, 0]
+            ]  # normalization gain whwh
+            imc = im0.copy() if save_crop else im0  # for save_crop
+            annotator = Annotator(
+                im0, line_width=line_thickness, example=str(names)
+            )
+            if len(det):
+                # Rescale boxes from img_size to im0 size
+                det[:, :4] = scale_boxes(
+                    im.shape[2:], det[:, :4], im0.shape
+                ).round()
+
+                # Print results
+                for c in det[:, 5].unique():
+                    n = (det[:, 5] == c).sum()  # detections per class
+                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
+
+                # Write results
+                for *xyxy, conf, cls in reversed(det):
+                    if save_txt:  # Write to file
+                        xywh = (
+                            (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn)
+                            .view(-1)
+                            .tolist()
+                        )  # normalized xywh
+                        line = (
+                            (cls, *xywh, conf) if save_conf else (cls, *xywh)
+                        )  # label format
+                        with open(f"{txt_path}.txt", "a") as f:
+                            f.write(("%g " * len(line)).rstrip() % line + "\n")
+
+                    if save_img or save_crop or view_img:  # Add bbox to image
+                        c = int(cls)  # integer class
+                        label = (
+                            None
+                            if hide_labels
+                            else (
+                                names[c]
+                                if hide_conf
+                                else f"{names[c]} {conf:.2f}"
+                            )
+                        )
+                        annotator.box_label(xyxy, label, color=colors(c, True))
+                    if save_crop:
+                        save_one_box(
+                            xyxy,
+                            imc,
+                            file=save_dir
+                            / "crops"
+                            / names[c]
+                            / f"{p.stem}.jpg",
+                            BGR=True,
+                        )
+
+            # Stream results
+            im0 = annotator.result()
+            if view_img:
+                if platform.system() == "Linux" and p not in windows:
+                    windows.append(p)
+                    cv2.namedWindow(
+                        str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO
+                    )  # allow window resize (Linux)
+                    cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])
+                cv2.imshow(str(p), im0)
+                cv2.waitKey(1)  # 1 millisecond
+
+            # Save results (image with detections)
+            if save_img:
+                if dataset.mode == "image":
+                    cv2.imwrite(save_path, im0)
+                else:  # 'video' or 'stream'
+                    if vid_path[i] != save_path:  # new video
+                        vid_path[i] = save_path
+                        if isinstance(vid_writer[i], cv2.VideoWriter):
+                            vid_writer[
+                                i
+                            ].release()  # release previous video writer
+                        if vid_cap:  # video
+                            fps = vid_cap.get(cv2.CAP_PROP_FPS)
+                            w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                            h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                        else:  # stream
+                            fps, w, h = 30, im0.shape[1], im0.shape[0]
+                        save_path = str(
+                            Path(save_path).with_suffix(".mp4")
+                        )  # force *.mp4 suffix on results videos
+                        vid_writer[i] = cv2.VideoWriter(
+                            save_path,
+                            cv2.VideoWriter_fourcc(*"mp4v"),
+                            fps,
+                            (w, h),
+                        )
+                    vid_writer[i].write(im0)
+
+        # Print time (inference-only)
+        LOGGER.info(
+            f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms"
+        )
+
+    # Print results
+    t = tuple(x.t / seen * 1e3 for x in dt)  # speeds per image
+    LOGGER.info(
+        f"Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}"
+        % t
+    )
+    if save_txt or save_img:
+        s = (
+            f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}"
+            if save_txt
+            else ""
+        )
+        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
+    if update:
+        strip_optimizer(
+            weights[0]
+        )  # update model (to fix SourceChangeWarning)
+
+
+def parse_opt():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--weights",
+        nargs="+",
+        type=str,
+        default=ROOT / "yolov5s.pt",
+        help="model path or triton URL",
+    )
+    parser.add_argument(
+        "--source",
+        type=str,
+        default=ROOT / "data/images",
+        help="file/dir/URL/glob/screen/0(webcam)",
+    )
+    parser.add_argument(
+        "--data",
+        type=str,
+        default=ROOT / "data/coco128.yaml",
+        help="(optional) dataset.yaml path",
+    )
+    parser.add_argument(
+        "--imgsz",
+        "--img",
+        "--img-size",
+        nargs="+",
+        type=int,
+        default=[640],
+        help="inference size h,w",
+    )
+    parser.add_argument(
+        "--conf-thres", type=float, default=0.25, help="confidence threshold"
+    )
+    parser.add_argument(
+        "--iou-thres", type=float, default=0.45, help="NMS IoU threshold"
+    )
+    parser.add_argument(
+        "--max-det",
+        type=int,
+        default=1000,
+        help="maximum detections per image",
+    )
+    parser.add_argument(
+        "--device", default="", help="cuda device, i.e. 0 or 0,1,2,3 or cpu"
+    )
+    parser.add_argument("--view-img", action="store_true", help="show results")
+    parser.add_argument(
+        "--save-txt", action="store_true", help="save results to *.txt"
+    )
+    parser.add_argument(
+        "--save-conf",
+        action="store_true",
+        help="save confidences in --save-txt labels",
+    )
+    parser.add_argument(
+        "--save-crop",
+        action="store_true",
+        help="save cropped prediction boxes",
+    )
+    parser.add_argument(
+        "--nosave", action="store_true", help="do not save images/videos"
+    )
+    parser.add_argument(
+        "--classes",
+        nargs="+",
+        type=int,
+        help="filter by class: --classes 0, or --classes 0 2 3",
+    )
+    parser.add_argument(
+        "--agnostic-nms", action="store_true", help="class-agnostic NMS"
+    )
+    parser.add_argument(
+        "--augment", action="store_true", help="augmented inference"
+    )
+    parser.add_argument(
+        "--visualize", action="store_true", help="visualize features"
+    )
+    parser.add_argument(
+        "--update", action="store_true", help="update all models"
+    )
+    parser.add_argument(
+        "--project",
+        default=ROOT / "runs/detect",
+        help="save results to project/name",
+    )
+    parser.add_argument(
+        "--name", default="exp", help="save results to project/name"
+    )
+    parser.add_argument(
+        "--exist-ok",
+        action="store_true",
+        help="existing project/name ok, do not increment",
+    )
+    parser.add_argument(
+        "--line-thickness",
+        default=3,
+        type=int,
+        help="bounding box thickness (pixels)",
+    )
+    parser.add_argument(
+        "--hide-labels", default=False, action="store_true", help="hide labels"
+    )
+    parser.add_argument(
+        "--hide-conf",
+        default=False,
+        action="store_true",
+        help="hide confidences",
+    )
+    parser.add_argument(
+        "--half", action="store_true", help="use FP16 half-precision inference"
+    )
+    parser.add_argument(
+        "--dnn", action="store_true", help="use OpenCV DNN for ONNX inference"
+    )
+    parser.add_argument(
+        "--vid-stride", type=int, default=1, help="video frame-rate stride"
+    )
+    opt = parser.parse_args()
+    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
+    print_args(vars(opt))
+    return opt
+
+
+def main(opt):
+    check_requirements(exclude=("tensorboard", "thop"))
+    run(**vars(opt))
+
+
+if __name__ == "__main__":
+    opt = parse_opt()
+    main(opt)

export.py

@@ -0,0 +1,1013 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Export a YOLOv5 PyTorch model to other formats. TensorFlow exports authored by https://github.com/zldrobit
+
+Format                      | `export.py --include`         | Model
+---                         | ---                           | ---
+PyTorch                     | -                             | yolov5s.pt
+TorchScript                 | `torchscript`                 | yolov5s.torchscript
+ONNX                        | `onnx`                        | yolov5s.onnx
+OpenVINO                    | `openvino`                    | yolov5s_openvino_model/
+TensorRT                    | `engine`                      | yolov5s.engine
+CoreML                      | `coreml`                      | yolov5s.mlmodel
+TensorFlow SavedModel       | `saved_model`                 | yolov5s_saved_model/
+TensorFlow GraphDef         | `pb`                          | yolov5s.pb
+TensorFlow Lite             | `tflite`                      | yolov5s.tflite
+TensorFlow Edge TPU         | `edgetpu`                     | yolov5s_edgetpu.tflite
+TensorFlow.js               | `tfjs`                        | yolov5s_web_model/
+PaddlePaddle                | `paddle`                      | yolov5s_paddle_model/
+
+Requirements:
+    $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime openvino-dev tensorflow-cpu  # CPU
+    $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime-gpu openvino-dev tensorflow  # GPU
+
+Usage:
+    $ python export.py --weights yolov5s.pt --include torchscript onnx openvino engine coreml tflite ...
+
+Inference:
+    $ python detect.py --weights yolov5s.pt                 # PyTorch
+                                 yolov5s.torchscript        # TorchScript
+                                 yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
+                                 yolov5s_openvino_model     # OpenVINO
+                                 yolov5s.engine             # TensorRT
+                                 yolov5s.mlmodel            # CoreML (macOS-only)
+                                 yolov5s_saved_model        # TensorFlow SavedModel
+                                 yolov5s.pb                 # TensorFlow GraphDef
+                                 yolov5s.tflite             # TensorFlow Lite
+                                 yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
+                                 yolov5s_paddle_model       # PaddlePaddle
+
+TensorFlow.js:
+    $ cd .. && git clone https://github.com/zldrobit/tfjs-yolov5-example.git && cd tfjs-yolov5-example
+    $ npm install
+    $ ln -s ../../yolov5/yolov5s_web_model public/yolov5s_web_model
+    $ npm start
+"""
+
+import argparse
+import contextlib
+import json
+import os
+import platform
+import re
+import subprocess
+import sys
+import time
+import warnings
+from pathlib import Path
+
+import pandas as pd
+import torch
+from torch.utils.mobile_optimizer import optimize_for_mobile
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[0]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+if platform.system() != "Windows":
+    ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+from models.experimental import attempt_load
+from models.yolo import ClassificationModel, Detect, DetectionModel, SegmentationModel
+from utils.dataloaders import LoadImages
+from utils.general import (
+    LOGGER,
+    Profile,
+    check_dataset,
+    check_img_size,
+    check_requirements,
+    check_version,
+    check_yaml,
+    colorstr,
+    file_size,
+    get_default_args,
+    print_args,
+    url2file,
+    yaml_save,
+)
+from utils.torch_utils import select_device, smart_inference_mode
+
+MACOS = platform.system() == "Darwin"  # macOS environment
+
+
+def export_formats():
+    # YOLOv5 export formats
+    x = [
+        ["PyTorch", "-", ".pt", True, True],
+        ["TorchScript", "torchscript", ".torchscript", True, True],
+        ["ONNX", "onnx", ".onnx", True, True],
+        ["OpenVINO", "openvino", "_openvino_model", True, False],
+        ["TensorRT", "engine", ".engine", False, True],
+        ["CoreML", "coreml", ".mlmodel", True, False],
+        ["TensorFlow SavedModel", "saved_model", "_saved_model", True, True],
+        ["TensorFlow GraphDef", "pb", ".pb", True, True],
+        ["TensorFlow Lite", "tflite", ".tflite", True, False],
+        ["TensorFlow Edge TPU", "edgetpu", "_edgetpu.tflite", False, False],
+        ["TensorFlow.js", "tfjs", "_web_model", False, False],
+        ["PaddlePaddle", "paddle", "_paddle_model", True, True],
+    ]
+    return pd.DataFrame(
+        x, columns=["Format", "Argument", "Suffix", "CPU", "GPU"]
+    )
+
+
+def try_export(inner_func):
+    # YOLOv5 export decorator, i..e @try_export
+    inner_args = get_default_args(inner_func)
+
+    def outer_func(*args, **kwargs):
+        prefix = inner_args["prefix"]
+        try:
+            with Profile() as dt:
+                f, model = inner_func(*args, **kwargs)
+            LOGGER.info(
+                f"{prefix} export success ✅ {dt.t:.1f}s, saved as {f} ({file_size(f):.1f} MB)"
+            )
+            return f, model
+        except Exception as e:
+            LOGGER.info(f"{prefix} export failure ❌ {dt.t:.1f}s: {e}")
+            return None, None
+
+    return outer_func
+
+
+@try_export
+def export_torchscript(
+    model, im, file, optimize, prefix=colorstr("TorchScript:")
+):
+    # YOLOv5 TorchScript model export
+    LOGGER.info(
+        f"\n{prefix} starting export with torch {torch.__version__}..."
+    )
+    f = file.with_suffix(".torchscript")
+
+    ts = torch.jit.trace(model, im, strict=False)
+    d = {
+        "shape": im.shape,
+        "stride": int(max(model.stride)),
+        "names": model.names,
+    }
+    extra_files = {"config.txt": json.dumps(d)}  # torch._C.ExtraFilesMap()
+    if (
+        optimize
+    ):  # https://pytorch.org/tutorials/recipes/mobile_interpreter.html
+        optimize_for_mobile(ts)._save_for_lite_interpreter(
+            str(f), _extra_files=extra_files
+        )
+    else:
+        ts.save(str(f), _extra_files=extra_files)
+    return f, None
+
+
+@try_export
+def export_onnx(
+    model, im, file, opset, dynamic, simplify, prefix=colorstr("ONNX:")
+):
+    # YOLOv5 ONNX export
+    check_requirements("onnx>=1.12.0")
+    import onnx
+
+    LOGGER.info(f"\n{prefix} starting export with onnx {onnx.__version__}...")
+    f = file.with_suffix(".onnx")
+
+    output_names = (
+        ["output0", "output1"]
+        if isinstance(model, SegmentationModel)
+        else ["output0"]
+    )
+    if dynamic:
+        dynamic = {
+            "images": {0: "batch", 2: "height", 3: "width"}
+        }  # shape(1,3,640,640)
+        if isinstance(model, SegmentationModel):
+            dynamic["output0"] = {
+                0: "batch",
+                1: "anchors",
+            }  # shape(1,25200,85)
+            dynamic["output1"] = {
+                0: "batch",
+                2: "mask_height",
+                3: "mask_width",
+            }  # shape(1,32,160,160)
+        elif isinstance(model, DetectionModel):
+            dynamic["output0"] = {
+                0: "batch",
+                1: "anchors",
+            }  # shape(1,25200,85)
+
+    torch.onnx.export(
+        model.cpu()
+        if dynamic
+        else model,  # --dynamic only compatible with cpu
+        im.cpu() if dynamic else im,
+        f,
+        verbose=False,
+        opset_version=opset,
+        do_constant_folding=True,  # WARNING: DNN inference with torch>=1.12 may require do_constant_folding=False
+        input_names=["images"],
+        output_names=output_names,
+        dynamic_axes=dynamic or None,
+    )
+
+    # Checks
+    model_onnx = onnx.load(f)  # load onnx model
+    onnx.checker.check_model(model_onnx)  # check onnx model
+
+    # Metadata
+    d = {"stride": int(max(model.stride)), "names": model.names}
+    for k, v in d.items():
+        meta = model_onnx.metadata_props.add()
+        meta.key, meta.value = k, str(v)
+    onnx.save(model_onnx, f)
+
+    # Simplify
+    if simplify:
+        try:
+            cuda = torch.cuda.is_available()
+            check_requirements(
+                (
+                    "onnxruntime-gpu" if cuda else "onnxruntime",
+                    "onnx-simplifier>=0.4.1",
+                )
+            )
+            import onnxsim
+
+            LOGGER.info(
+                f"{prefix} simplifying with onnx-simplifier {onnxsim.__version__}..."
+            )
+            model_onnx, check = onnxsim.simplify(model_onnx)
+            assert check, "assert check failed"
+            onnx.save(model_onnx, f)
+        except Exception as e:
+            LOGGER.info(f"{prefix} simplifier failure: {e}")
+    return f, model_onnx
+
+
+@try_export
+def export_openvino(file, metadata, half, prefix=colorstr("OpenVINO:")):
+    # YOLOv5 OpenVINO export
+    check_requirements(
+        "openvino-dev"
+    )  # requires openvino-dev: https://pypi.org/project/openvino-dev/
+    import openvino.inference_engine as ie
+
+    LOGGER.info(
+        f"\n{prefix} starting export with openvino {ie.__version__}..."
+    )
+    f = str(file).replace(".pt", f"_openvino_model{os.sep}")
+
+    cmd = f"mo --input_model {file.with_suffix('.onnx')} --output_dir {f} --data_type {'FP16' if half else 'FP32'}"
+    subprocess.run(cmd.split(), check=True, env=os.environ)  # export
+    yaml_save(
+        Path(f) / file.with_suffix(".yaml").name, metadata
+    )  # add metadata.yaml
+    return f, None
+
+
+@try_export
+def export_paddle(model, im, file, metadata, prefix=colorstr("PaddlePaddle:")):
+    # YOLOv5 Paddle export
+    check_requirements(("paddlepaddle", "x2paddle"))
+    import x2paddle
+    from x2paddle.convert import pytorch2paddle
+
+    LOGGER.info(
+        f"\n{prefix} starting export with X2Paddle {x2paddle.__version__}..."
+    )
+    f = str(file).replace(".pt", f"_paddle_model{os.sep}")
+
+    pytorch2paddle(
+        module=model, save_dir=f, jit_type="trace", input_examples=[im]
+    )  # export
+    yaml_save(
+        Path(f) / file.with_suffix(".yaml").name, metadata
+    )  # add metadata.yaml
+    return f, None
+
+
+@try_export
+def export_coreml(model, im, file, int8, half, prefix=colorstr("CoreML:")):
+    # YOLOv5 CoreML export
+    check_requirements("coremltools")
+    import coremltools as ct
+
+    LOGGER.info(
+        f"\n{prefix} starting export with coremltools {ct.__version__}..."
+    )
+    f = file.with_suffix(".mlmodel")
+
+    ts = torch.jit.trace(model, im, strict=False)  # TorchScript model
+    ct_model = ct.convert(
+        ts,
+        inputs=[
+            ct.ImageType(
+                "image", shape=im.shape, scale=1 / 255, bias=[0, 0, 0]
+            )
+        ],
+    )
+    bits, mode = (
+        (8, "kmeans_lut") if int8 else (16, "linear") if half else (32, None)
+    )
+    if bits < 32:
+        if MACOS:  # quantization only supported on macOS
+            with warnings.catch_warnings():
+                warnings.filterwarnings(
+                    "ignore", category=DeprecationWarning
+                )  # suppress numpy==1.20 float warning
+                ct_model = ct.models.neural_network.quantization_utils.quantize_weights(
+                    ct_model, bits, mode
+                )
+        else:
+            print(
+                f"{prefix} quantization only supported on macOS, skipping..."
+            )
+    ct_model.save(f)
+    return f, ct_model
+
+
+@try_export
+def export_engine(
+    model,
+    im,
+    file,
+    half,
+    dynamic,
+    simplify,
+    workspace=4,
+    verbose=False,
+    prefix=colorstr("TensorRT:"),
+):
+    # YOLOv5 TensorRT export https://developer.nvidia.com/tensorrt
+    assert (
+        im.device.type != "cpu"
+    ), "export running on CPU but must be on GPU, i.e. `python export.py --device 0`"
+    try:
+        import tensorrt as trt
+    except Exception:
+        if platform.system() == "Linux":
+            check_requirements(
+                "nvidia-tensorrt",
+                cmds="-U --index-url https://pypi.ngc.nvidia.com",
+            )
+        import tensorrt as trt
+
+    if (
+        trt.__version__[0] == "7"
+    ):  # TensorRT 7 handling https://github.com/ultralytics/yolov5/issues/6012
+        grid = model.model[-1].anchor_grid
+        model.model[-1].anchor_grid = [a[..., :1, :1, :] for a in grid]
+        export_onnx(model, im, file, 12, dynamic, simplify)  # opset 12
+        model.model[-1].anchor_grid = grid
+    else:  # TensorRT >= 8
+        check_version(
+            trt.__version__, "8.0.0", hard=True
+        )  # require tensorrt>=8.0.0
+        export_onnx(model, im, file, 12, dynamic, simplify)  # opset 12
+    onnx = file.with_suffix(".onnx")
+
+    LOGGER.info(
+        f"\n{prefix} starting export with TensorRT {trt.__version__}..."
+    )
+    assert onnx.exists(), f"failed to export ONNX file: {onnx}"
+    f = file.with_suffix(".engine")  # TensorRT engine file
+    logger = trt.Logger(trt.Logger.INFO)
+    if verbose:
+        logger.min_severity = trt.Logger.Severity.VERBOSE
+
+    builder = trt.Builder(logger)
+    config = builder.create_builder_config()
+    config.max_workspace_size = workspace * 1 << 30
+    # config.set_memory_pool_limit(trt.MemoryPoolType.WORKSPACE, workspace << 30)  # fix TRT 8.4 deprecation notice
+
+    flag = 1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH)
+    network = builder.create_network(flag)
+    parser = trt.OnnxParser(network, logger)
+    if not parser.parse_from_file(str(onnx)):
+        raise RuntimeError(f"failed to load ONNX file: {onnx}")
+
+    inputs = [network.get_input(i) for i in range(network.num_inputs)]
+    outputs = [network.get_output(i) for i in range(network.num_outputs)]
+    for inp in inputs:
+        LOGGER.info(
+            f'{prefix} input "{inp.name}" with shape{inp.shape} {inp.dtype}'
+        )
+    for out in outputs:
+        LOGGER.info(
+            f'{prefix} output "{out.name}" with shape{out.shape} {out.dtype}'
+        )
+
+    if dynamic:
+        if im.shape[0] <= 1:
+            LOGGER.warning(
+                f"{prefix} WARNING ⚠️ --dynamic model requires maximum --batch-size argument"
+            )
+        profile = builder.create_optimization_profile()
+        for inp in inputs:
+            profile.set_shape(
+                inp.name,
+                (1, *im.shape[1:]),
+                (max(1, im.shape[0] // 2), *im.shape[1:]),
+                im.shape,
+            )
+        config.add_optimization_profile(profile)
+
+    LOGGER.info(
+        f"{prefix} building FP{16 if builder.platform_has_fast_fp16 and half else 32} engine as {f}"
+    )
+    if builder.platform_has_fast_fp16 and half:
+        config.set_flag(trt.BuilderFlag.FP16)
+    with builder.build_engine(network, config) as engine, open(f, "wb") as t:
+        t.write(engine.serialize())
+    return f, None
+
+
+@try_export
+def export_saved_model(
+    model,
+    im,
+    file,
+    dynamic,
+    tf_nms=False,
+    agnostic_nms=False,
+    topk_per_class=100,
+    topk_all=100,
+    iou_thres=0.45,
+    conf_thres=0.25,
+    keras=False,
+    prefix=colorstr("TensorFlow SavedModel:"),
+):
+    # YOLOv5 TensorFlow SavedModel export
+    try:
+        import tensorflow as tf
+    except Exception:
+        check_requirements(
+            f"tensorflow{'' if torch.cuda.is_available() else '-macos' if MACOS else '-cpu'}"
+        )
+        import tensorflow as tf
+    from tensorflow.python.framework.convert_to_constants import (
+        convert_variables_to_constants_v2,
+    )
+
+    from models.tf import TFModel
+
+    LOGGER.info(
+        f"\n{prefix} starting export with tensorflow {tf.__version__}..."
+    )
+    f = str(file).replace(".pt", "_saved_model")
+    batch_size, ch, *imgsz = list(im.shape)  # BCHW
+
+    tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
+    im = tf.zeros((batch_size, *imgsz, ch))  # BHWC order for TensorFlow
+    _ = tf_model.predict(
+        im,
+        tf_nms,
+        agnostic_nms,
+        topk_per_class,
+        topk_all,
+        iou_thres,
+        conf_thres,
+    )
+    inputs = tf.keras.Input(
+        shape=(*imgsz, ch), batch_size=None if dynamic else batch_size
+    )
+    outputs = tf_model.predict(
+        inputs,
+        tf_nms,
+        agnostic_nms,
+        topk_per_class,
+        topk_all,
+        iou_thres,
+        conf_thres,
+    )
+    keras_model = tf.keras.Model(inputs=inputs, outputs=outputs)
+    keras_model.trainable = False
+    keras_model.summary()
+    if keras:
+        keras_model.save(f, save_format="tf")
+    else:
+        spec = tf.TensorSpec(
+            keras_model.inputs[0].shape, keras_model.inputs[0].dtype
+        )
+        m = tf.function(lambda x: keras_model(x))  # full model
+        m = m.get_concrete_function(spec)
+        frozen_func = convert_variables_to_constants_v2(m)
+        tfm = tf.Module()
+        tfm.__call__ = tf.function(
+            lambda x: frozen_func(x)[:4] if tf_nms else frozen_func(x), [spec]
+        )
+        tfm.__call__(im)
+        tf.saved_model.save(
+            tfm,
+            f,
+            options=tf.saved_model.SaveOptions(
+                experimental_custom_gradients=False
+            )
+            if check_version(tf.__version__, "2.6")
+            else tf.saved_model.SaveOptions(),
+        )
+    return f, keras_model
+
+
+@try_export
+def export_pb(keras_model, file, prefix=colorstr("TensorFlow GraphDef:")):
+    # YOLOv5 TensorFlow GraphDef *.pb export https://github.com/leimao/Frozen_Graph_TensorFlow
+    import tensorflow as tf
+    from tensorflow.python.framework.convert_to_constants import (
+        convert_variables_to_constants_v2,
+    )
+
+    LOGGER.info(
+        f"\n{prefix} starting export with tensorflow {tf.__version__}..."
+    )
+    f = file.with_suffix(".pb")
+
+    m = tf.function(lambda x: keras_model(x))  # full model
+    m = m.get_concrete_function(
+        tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype)
+    )
+    frozen_func = convert_variables_to_constants_v2(m)
+    frozen_func.graph.as_graph_def()
+    tf.io.write_graph(
+        graph_or_graph_def=frozen_func.graph,
+        logdir=str(f.parent),
+        name=f.name,
+        as_text=False,
+    )
+    return f, None
+
+
+@try_export
+def export_tflite(
+    keras_model,
+    im,
+    file,
+    int8,
+    data,
+    nms,
+    agnostic_nms,
+    prefix=colorstr("TensorFlow Lite:"),
+):
+    # YOLOv5 TensorFlow Lite export
+    import tensorflow as tf
+
+    LOGGER.info(
+        f"\n{prefix} starting export with tensorflow {tf.__version__}..."
+    )
+    batch_size, ch, *imgsz = list(im.shape)  # BCHW
+    f = str(file).replace(".pt", "-fp16.tflite")
+
+    converter = tf.lite.TFLiteConverter.from_keras_model(keras_model)
+    converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS]
+    converter.target_spec.supported_types = [tf.float16]
+    converter.optimizations = [tf.lite.Optimize.DEFAULT]
+    if int8:
+        from models.tf import representative_dataset_gen
+
+        dataset = LoadImages(
+            check_dataset(check_yaml(data))["train"],
+            img_size=imgsz,
+            auto=False,
+        )
+        converter.representative_dataset = lambda: representative_dataset_gen(
+            dataset, ncalib=100
+        )
+        converter.target_spec.supported_ops = [
+            tf.lite.OpsSet.TFLITE_BUILTINS_INT8
+        ]
+        converter.target_spec.supported_types = []
+        converter.inference_input_type = tf.uint8  # or tf.int8
+        converter.inference_output_type = tf.uint8  # or tf.int8
+        converter.experimental_new_quantizer = True
+        f = str(file).replace(".pt", "-int8.tflite")
+    if nms or agnostic_nms:
+        converter.target_spec.supported_ops.append(
+            tf.lite.OpsSet.SELECT_TF_OPS
+        )
+
+    tflite_model = converter.convert()
+    open(f, "wb").write(tflite_model)
+    return f, None
+
+
+@try_export
+def export_edgetpu(file, prefix=colorstr("Edge TPU:")):
+    # YOLOv5 Edge TPU export https://coral.ai/docs/edgetpu/models-intro/
+    cmd = "edgetpu_compiler --version"
+    help_url = "https://coral.ai/docs/edgetpu/compiler/"
+    assert (
+        platform.system() == "Linux"
+    ), f"export only supported on Linux. See {help_url}"
+    if subprocess.run(f"{cmd} >/dev/null", shell=True).returncode != 0:
+        LOGGER.info(
+            f"\n{prefix} export requires Edge TPU compiler. Attempting install from {help_url}"
+        )
+        sudo = (
+            subprocess.run("sudo --version >/dev/null", shell=True).returncode
+            == 0
+        )  # sudo installed on system
+        for c in (
+            "curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -",
+            'echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | sudo tee /etc/apt/sources.list.d/coral-edgetpu.list',
+            "sudo apt-get update",
+            "sudo apt-get install edgetpu-compiler",
+        ):
+            subprocess.run(
+                c if sudo else c.replace("sudo ", ""), shell=True, check=True
+            )
+    ver = (
+        subprocess.run(cmd, shell=True, capture_output=True, check=True)
+        .stdout.decode()
+        .split()[-1]
+    )
+
+    LOGGER.info(f"\n{prefix} starting export with Edge TPU compiler {ver}...")
+    f = str(file).replace(".pt", "-int8_edgetpu.tflite")  # Edge TPU model
+    f_tfl = str(file).replace(".pt", "-int8.tflite")  # TFLite model
+
+    cmd = f"edgetpu_compiler -s -d -k 10 --out_dir {file.parent} {f_tfl}"
+    subprocess.run(cmd.split(), check=True)
+    return f, None
+
+
+@try_export
+def export_tfjs(file, prefix=colorstr("TensorFlow.js:")):
+    # YOLOv5 TensorFlow.js export
+    check_requirements("tensorflowjs")
+    import tensorflowjs as tfjs
+
+    LOGGER.info(
+        f"\n{prefix} starting export with tensorflowjs {tfjs.__version__}..."
+    )
+    f = str(file).replace(".pt", "_web_model")  # js dir
+    f_pb = file.with_suffix(".pb")  # *.pb path
+    f_json = f"{f}/model.json"  # *.json path
+
+    cmd = (
+        f"tensorflowjs_converter --input_format=tf_frozen_model "
+        f"--output_node_names=Identity,Identity_1,Identity_2,Identity_3 {f_pb} {f}"
+    )
+    subprocess.run(cmd.split())
+
+    json = Path(f_json).read_text()
+    with open(f_json, "w") as j:  # sort JSON Identity_* in ascending order
+        subst = re.sub(
+            r'{"outputs": {"Identity.?.?": {"name": "Identity.?.?"}, '
+            r'"Identity.?.?": {"name": "Identity.?.?"}, '
+            r'"Identity.?.?": {"name": "Identity.?.?"}, '
+            r'"Identity.?.?": {"name": "Identity.?.?"}}}',
+            r'{"outputs": {"Identity": {"name": "Identity"}, '
+            r'"Identity_1": {"name": "Identity_1"}, '
+            r'"Identity_2": {"name": "Identity_2"}, '
+            r'"Identity_3": {"name": "Identity_3"}}}',
+            json,
+        )
+        j.write(subst)
+    return f, None
+
+
+def add_tflite_metadata(file, metadata, num_outputs):
+    # Add metadata to *.tflite models per https://www.tensorflow.org/lite/models/convert/metadata
+    with contextlib.suppress(ImportError):
+        # check_requirements('tflite_support')
+        from tflite_support import flatbuffers
+        from tflite_support import metadata as _metadata
+        from tflite_support import metadata_schema_py_generated as _metadata_fb
+
+        tmp_file = Path("/tmp/meta.txt")
+        with open(tmp_file, "w") as meta_f:
+            meta_f.write(str(metadata))
+
+        model_meta = _metadata_fb.ModelMetadataT()
+        label_file = _metadata_fb.AssociatedFileT()
+        label_file.name = tmp_file.name
+        model_meta.associatedFiles = [label_file]
+
+        subgraph = _metadata_fb.SubGraphMetadataT()
+        subgraph.inputTensorMetadata = [_metadata_fb.TensorMetadataT()]
+        subgraph.outputTensorMetadata = [
+            _metadata_fb.TensorMetadataT()
+        ] * num_outputs
+        model_meta.subgraphMetadata = [subgraph]
+
+        b = flatbuffers.Builder(0)
+        b.Finish(
+            model_meta.Pack(b),
+            _metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER,
+        )
+        metadata_buf = b.Output()
+
+        populator = _metadata.MetadataPopulator.with_model_file(file)
+        populator.load_metadata_buffer(metadata_buf)
+        populator.load_associated_files([str(tmp_file)])
+        populator.populate()
+        tmp_file.unlink()
+
+
+@smart_inference_mode()
+def run(
+    data=ROOT / "data/coco128.yaml",  # 'dataset.yaml path'
+    weights=ROOT / "yolov5s.pt",  # weights path
+    imgsz=(640, 640),  # image (height, width)
+    batch_size=1,  # batch size
+    device="cpu",  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+    include=("torchscript", "onnx"),  # include formats
+    half=False,  # FP16 half-precision export
+    inplace=False,  # set YOLOv5 Detect() inplace=True
+    keras=False,  # use Keras
+    optimize=False,  # TorchScript: optimize for mobile
+    int8=False,  # CoreML/TF INT8 quantization
+    dynamic=False,  # ONNX/TF/TensorRT: dynamic axes
+    simplify=False,  # ONNX: simplify model
+    opset=12,  # ONNX: opset version
+    verbose=False,  # TensorRT: verbose log
+    workspace=4,  # TensorRT: workspace size (GB)
+    nms=False,  # TF: add NMS to model
+    agnostic_nms=False,  # TF: add agnostic NMS to model
+    topk_per_class=100,  # TF.js NMS: topk per class to keep
+    topk_all=100,  # TF.js NMS: topk for all classes to keep
+    iou_thres=0.45,  # TF.js NMS: IoU threshold
+    conf_thres=0.25,  # TF.js NMS: confidence threshold
+):
+    t = time.time()
+    include = [x.lower() for x in include]  # to lowercase
+    fmts = tuple(export_formats()["Argument"][1:])  # --include arguments
+    flags = [x in include for x in fmts]
+    assert sum(flags) == len(
+        include
+    ), f"ERROR: Invalid --include {include}, valid --include arguments are {fmts}"
+    (
+        jit,
+        onnx,
+        xml,
+        engine,
+        coreml,
+        saved_model,
+        pb,
+        tflite,
+        edgetpu,
+        tfjs,
+        paddle,
+    ) = flags  # export booleans
+    file = Path(
+        url2file(weights)
+        if str(weights).startswith(("http:/", "https:/"))
+        else weights
+    )  # PyTorch weights
+
+    # Load PyTorch model
+    device = select_device(device)
+    if half:
+        assert (
+            device.type != "cpu" or coreml
+        ), "--half only compatible with GPU export, i.e. use --device 0"
+        assert (
+            not dynamic
+        ), "--half not compatible with --dynamic, i.e. use either --half or --dynamic but not both"
+    model = attempt_load(
+        weights, device=device, inplace=True, fuse=True
+    )  # load FP32 model
+
+    # Checks
+    imgsz *= 2 if len(imgsz) == 1 else 1  # expand
+    if optimize:
+        assert (
+            device.type == "cpu"
+        ), "--optimize not compatible with cuda devices, i.e. use --device cpu"
+
+    # Input
+    gs = int(max(model.stride))  # grid size (max stride)
+    imgsz = [
+        check_img_size(x, gs) for x in imgsz
+    ]  # verify img_size are gs-multiples
+    im = torch.zeros(batch_size, 3, *imgsz).to(
+        device
+    )  # image size(1,3,320,192) BCHW iDetection
+
+    # Update model
+    model.eval()
+    for k, m in model.named_modules():
+        if isinstance(m, Detect):
+            m.inplace = inplace
+            m.dynamic = dynamic
+            m.export = True
+
+    for _ in range(2):
+        y = model(im)  # dry runs
+    if half and not coreml:
+        im, model = im.half(), model.half()  # to FP16
+    shape = tuple(
+        (y[0] if isinstance(y, tuple) else y).shape
+    )  # model output shape
+    metadata = {
+        "stride": int(max(model.stride)),
+        "names": model.names,
+    }  # model metadata
+    LOGGER.info(
+        f"\n{colorstr('PyTorch:')} starting from {file} with output shape {shape} ({file_size(file):.1f} MB)"
+    )
+
+    # Exports
+    f = [""] * len(fmts)  # exported filenames
+    warnings.filterwarnings(
+        action="ignore", category=torch.jit.TracerWarning
+    )  # suppress TracerWarning
+    if jit:  # TorchScript
+        f[0], _ = export_torchscript(model, im, file, optimize)
+    if engine:  # TensorRT required before ONNX
+        f[1], _ = export_engine(
+            model, im, file, half, dynamic, simplify, workspace, verbose
+        )
+    if onnx or xml:  # OpenVINO requires ONNX
+        f[2], _ = export_onnx(model, im, file, opset, dynamic, simplify)
+    if xml:  # OpenVINO
+        f[3], _ = export_openvino(file, metadata, half)
+    if coreml:  # CoreML
+        f[4], _ = export_coreml(model, im, file, int8, half)
+    if any((saved_model, pb, tflite, edgetpu, tfjs)):  # TensorFlow formats
+        assert (
+            not tflite or not tfjs
+        ), "TFLite and TF.js models must be exported separately, please pass only one type."
+        assert not isinstance(
+            model, ClassificationModel
+        ), "ClassificationModel export to TF formats not yet supported."
+        f[5], s_model = export_saved_model(
+            model.cpu(),
+            im,
+            file,
+            dynamic,
+            tf_nms=nms or agnostic_nms or tfjs,
+            agnostic_nms=agnostic_nms or tfjs,
+            topk_per_class=topk_per_class,
+            topk_all=topk_all,
+            iou_thres=iou_thres,
+            conf_thres=conf_thres,
+            keras=keras,
+        )
+        if pb or tfjs:  # pb prerequisite to tfjs
+            f[6], _ = export_pb(s_model, file)
+        if tflite or edgetpu:
+            f[7], _ = export_tflite(
+                s_model,
+                im,
+                file,
+                int8 or edgetpu,
+                data=data,
+                nms=nms,
+                agnostic_nms=agnostic_nms,
+            )
+            if edgetpu:
+                f[8], _ = export_edgetpu(file)
+            add_tflite_metadata(
+                f[8] or f[7], metadata, num_outputs=len(s_model.outputs)
+            )
+        if tfjs:
+            f[9], _ = export_tfjs(file)
+    if paddle:  # PaddlePaddle
+        f[10], _ = export_paddle(model, im, file, metadata)
+
+    # Finish
+    f = [str(x) for x in f if x]  # filter out '' and None
+    if any(f):
+        cls, det, seg = (
+            isinstance(model, x)
+            for x in (ClassificationModel, DetectionModel, SegmentationModel)
+        )  # type
+        det &= (
+            not seg
+        )  # segmentation models inherit from SegmentationModel(DetectionModel)
+        dir = Path("segment" if seg else "classify" if cls else "")
+        h = "--half" if half else ""  # --half FP16 inference arg
+        s = (
+            "# WARNING ⚠️ ClassificationModel not yet supported for PyTorch Hub AutoShape inference"
+            if cls
+            else "# WARNING ⚠️ SegmentationModel not yet supported for PyTorch Hub AutoShape inference"
+            if seg
+            else ""
+        )
+        LOGGER.info(
+            f"\nExport complete ({time.time() - t:.1f}s)"
+            f"\nResults saved to {colorstr('bold', file.parent.resolve())}"
+            f"\nDetect:          python {dir / ('detect.py' if det else 'predict.py')} --weights {f[-1]} {h}"
+            f"\nValidate:        python {dir / 'val.py'} --weights {f[-1]} {h}"
+            f"\nPyTorch Hub:     model = torch.hub.load('ultralytics/yolov5', 'custom', '{f[-1]}')  {s}"
+            f"\nVisualize:       https://netron.app"
+        )
+    return f  # return list of exported files/dirs
+
+
+def parse_opt():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--data",
+        type=str,
+        default=ROOT / "data/coco128.yaml",
+        help="dataset.yaml path",
+    )
+    parser.add_argument(
+        "--weights",
+        nargs="+",
+        type=str,
+        default=ROOT / "yolov5s.pt",
+        help="model.pt path(s)",
+    )
+    parser.add_argument(
+        "--imgsz",
+        "--img",
+        "--img-size",
+        nargs="+",
+        type=int,
+        default=[640, 640],
+        help="image (h, w)",
+    )
+    parser.add_argument("--batch-size", type=int, default=1, help="batch size")
+    parser.add_argument(
+        "--device", default="cpu", help="cuda device, i.e. 0 or 0,1,2,3 or cpu"
+    )
+    parser.add_argument(
+        "--half", action="store_true", help="FP16 half-precision export"
+    )
+    parser.add_argument(
+        "--inplace",
+        action="store_true",
+        help="set YOLOv5 Detect() inplace=True",
+    )
+    parser.add_argument("--keras", action="store_true", help="TF: use Keras")
+    parser.add_argument(
+        "--optimize",
+        action="store_true",
+        help="TorchScript: optimize for mobile",
+    )
+    parser.add_argument(
+        "--int8", action="store_true", help="CoreML/TF INT8 quantization"
+    )
+    parser.add_argument(
+        "--dynamic", action="store_true", help="ONNX/TF/TensorRT: dynamic axes"
+    )
+    parser.add_argument(
+        "--simplify", action="store_true", help="ONNX: simplify model"
+    )
+    parser.add_argument(
+        "--opset", type=int, default=17, help="ONNX: opset version"
+    )
+    parser.add_argument(
+        "--verbose", action="store_true", help="TensorRT: verbose log"
+    )
+    parser.add_argument(
+        "--workspace",
+        type=int,
+        default=4,
+        help="TensorRT: workspace size (GB)",
+    )
+    parser.add_argument(
+        "--nms", action="store_true", help="TF: add NMS to model"
+    )
+    parser.add_argument(
+        "--agnostic-nms",
+        action="store_true",
+        help="TF: add agnostic NMS to model",
+    )
+    parser.add_argument(
+        "--topk-per-class",
+        type=int,
+        default=100,
+        help="TF.js NMS: topk per class to keep",
+    )
+    parser.add_argument(
+        "--topk-all",
+        type=int,
+        default=100,
+        help="TF.js NMS: topk for all classes to keep",
+    )
+    parser.add_argument(
+        "--iou-thres",
+        type=float,
+        default=0.45,
+        help="TF.js NMS: IoU threshold",
+    )
+    parser.add_argument(
+        "--conf-thres",
+        type=float,
+        default=0.25,
+        help="TF.js NMS: confidence threshold",
+    )
+    parser.add_argument(
+        "--include",
+        nargs="+",
+        default=["torchscript"],
+        help="torchscript, onnx, openvino, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle",
+    )
+    opt = parser.parse_args()
+    print_args(vars(opt))
+    return opt
+
+
+def main(opt):
+    for opt.weights in (
+        opt.weights if isinstance(opt.weights, list) else [opt.weights]
+    ):
+        run(**vars(opt))
+
+
+if __name__ == "__main__":
+    opt = parse_opt()
+    main(opt)

hubconf.py

@@ -0,0 +1,309 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+PyTorch Hub models https://pytorch.org/hub/ultralytics_yolov5
+
+Usage:
+    import torch
+    model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # official model
+    model = torch.hub.load('ultralytics/yolov5:master', 'yolov5s')  # from branch
+    model = torch.hub.load('ultralytics/yolov5', 'custom', 'yolov5s.pt')  # custom/local model
+    model = torch.hub.load('.', 'custom', 'yolov5s.pt', source='local')  # local repo
+"""
+
+import torch
+
+
+def _create(
+    name,
+    pretrained=True,
+    channels=3,
+    classes=80,
+    autoshape=True,
+    verbose=True,
+    device=None,
+):
+    """Creates or loads a YOLOv5 model
+
+    Arguments:
+        name (str): model name 'yolov5s' or path 'path/to/best.pt'
+        pretrained (bool): load pretrained weights into the model
+        channels (int): number of input channels
+        classes (int): number of model classes
+        autoshape (bool): apply YOLOv5 .autoshape() wrapper to model
+        verbose (bool): print all information to screen
+        device (str, torch.device, None): device to use for model parameters
+
+    Returns:
+        YOLOv5 model
+    """
+    from pathlib import Path
+
+    from models.common import AutoShape, DetectMultiBackend
+    from models.experimental import attempt_load
+    from models.yolo import ClassificationModel, DetectionModel, SegmentationModel
+    from utils.downloads import attempt_download
+    from utils.general import LOGGER, check_requirements, intersect_dicts, logging
+    from utils.torch_utils import select_device
+
+    if not verbose:
+        LOGGER.setLevel(logging.WARNING)
+    check_requirements(exclude=("opencv-python", "tensorboard", "thop"))
+    name = Path(name)
+    path = (
+        name.with_suffix(".pt")
+        if name.suffix == "" and not name.is_dir()
+        else name
+    )  # checkpoint path
+    try:
+        device = select_device(device)
+        if pretrained and channels == 3 and classes == 80:
+            try:
+                model = DetectMultiBackend(
+                    path, device=device, fuse=autoshape
+                )  # detection model
+                if autoshape:
+                    if model.pt and isinstance(
+                        model.model, ClassificationModel
+                    ):
+                        LOGGER.warning(
+                            "WARNING ⚠️ YOLOv5 ClassificationModel is not yet AutoShape compatible. "
+                            "You must pass torch tensors in BCHW to this model, i.e. shape(1,3,224,224)."
+                        )
+                    elif model.pt and isinstance(
+                        model.model, SegmentationModel
+                    ):
+                        LOGGER.warning(
+                            "WARNING ⚠️ YOLOv5 SegmentationModel is not yet AutoShape compatible. "
+                            "You will not be able to run inference with this model."
+                        )
+                    else:
+                        model = AutoShape(
+                            model
+                        )  # for file/URI/PIL/cv2/np inputs and NMS
+            except Exception:
+                model = attempt_load(
+                    path, device=device, fuse=False
+                )  # arbitrary model
+        else:
+            cfg = list(
+                (Path(__file__).parent / "models").rglob(f"{path.stem}.yaml")
+            )[
+                0
+            ]  # model.yaml path
+            model = DetectionModel(cfg, channels, classes)  # create model
+            if pretrained:
+                ckpt = torch.load(
+                    attempt_download(path), map_location=device
+                )  # load
+                csd = (
+                    ckpt["model"].float().state_dict()
+                )  # checkpoint state_dict as FP32
+                csd = intersect_dicts(
+                    csd, model.state_dict(), exclude=["anchors"]
+                )  # intersect
+                model.load_state_dict(csd, strict=False)  # load
+                if len(ckpt["model"].names) == classes:
+                    model.names = ckpt[
+                        "model"
+                    ].names  # set class names attribute
+        if not verbose:
+            LOGGER.setLevel(logging.INFO)  # reset to default
+        return model.to(device)
+
+    except Exception as e:
+        help_url = "https://github.com/ultralytics/yolov5/issues/36"
+        s = f"{e}. Cache may be out of date, try `force_reload=True` or see {help_url} for help."
+        raise Exception(s) from e
+
+
+def custom(
+    path="path/to/model.pt", autoshape=True, _verbose=True, device=None
+):
+    # YOLOv5 custom or local model
+    return _create(path, autoshape=autoshape, verbose=_verbose, device=device)
+
+
+def yolov5n(
+    pretrained=True,
+    channels=3,
+    classes=80,
+    autoshape=True,
+    _verbose=True,
+    device=None,
+):
+    # YOLOv5-nano model https://github.com/ultralytics/yolov5
+    return _create(
+        "yolov5n", pretrained, channels, classes, autoshape, _verbose, device
+    )
+
+
+def yolov5s(
+    pretrained=True,
+    channels=3,
+    classes=80,
+    autoshape=True,
+    _verbose=True,
+    device=None,
+):
+    # YOLOv5-small model https://github.com/ultralytics/yolov5
+    return _create(
+        "yolov5s", pretrained, channels, classes, autoshape, _verbose, device
+    )
+
+
+def yolov5m(
+    pretrained=True,
+    channels=3,
+    classes=80,
+    autoshape=True,
+    _verbose=True,
+    device=None,
+):
+    # YOLOv5-medium model https://github.com/ultralytics/yolov5
+    return _create(
+        "yolov5m", pretrained, channels, classes, autoshape, _verbose, device
+    )
+
+
+def yolov5l(
+    pretrained=True,
+    channels=3,
+    classes=80,
+    autoshape=True,
+    _verbose=True,
+    device=None,
+):
+    # YOLOv5-large model https://github.com/ultralytics/yolov5
+    return _create(
+        "yolov5l", pretrained, channels, classes, autoshape, _verbose, device
+    )
+
+
+def yolov5x(
+    pretrained=True,
+    channels=3,
+    classes=80,
+    autoshape=True,
+    _verbose=True,
+    device=None,
+):
+    # YOLOv5-xlarge model https://github.com/ultralytics/yolov5
+    return _create(
+        "yolov5x", pretrained, channels, classes, autoshape, _verbose, device
+    )
+
+
+def yolov5n6(
+    pretrained=True,
+    channels=3,
+    classes=80,
+    autoshape=True,
+    _verbose=True,
+    device=None,
+):
+    # YOLOv5-nano-P6 model https://github.com/ultralytics/yolov5
+    return _create(
+        "yolov5n6", pretrained, channels, classes, autoshape, _verbose, device
+    )
+
+
+def yolov5s6(
+    pretrained=True,
+    channels=3,
+    classes=80,
+    autoshape=True,
+    _verbose=True,
+    device=None,
+):
+    # YOLOv5-small-P6 model https://github.com/ultralytics/yolov5
+    return _create(
+        "yolov5s6", pretrained, channels, classes, autoshape, _verbose, device
+    )
+
+
+def yolov5m6(
+    pretrained=True,
+    channels=3,
+    classes=80,
+    autoshape=True,
+    _verbose=True,
+    device=None,
+):
+    # YOLOv5-medium-P6 model https://github.com/ultralytics/yolov5
+    return _create(
+        "yolov5m6", pretrained, channels, classes, autoshape, _verbose, device
+    )
+
+
+def yolov5l6(
+    pretrained=True,
+    channels=3,
+    classes=80,
+    autoshape=True,
+    _verbose=True,
+    device=None,
+):
+    # YOLOv5-large-P6 model https://github.com/ultralytics/yolov5
+    return _create(
+        "yolov5l6", pretrained, channels, classes, autoshape, _verbose, device
+    )
+
+
+def yolov5x6(
+    pretrained=True,
+    channels=3,
+    classes=80,
+    autoshape=True,
+    _verbose=True,
+    device=None,
+):
+    # YOLOv5-xlarge-P6 model https://github.com/ultralytics/yolov5
+    return _create(
+        "yolov5x6", pretrained, channels, classes, autoshape, _verbose, device
+    )
+
+
+if __name__ == "__main__":
+    import argparse
+    from pathlib import Path
+
+    import numpy as np
+    from PIL import Image
+
+    from utils.general import cv2, print_args
+
+    # Argparser
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--model", type=str, default="yolov5s", help="model name"
+    )
+    opt = parser.parse_args()
+    print_args(vars(opt))
+
+    # Model
+    model = _create(
+        name=opt.model,
+        pretrained=True,
+        channels=3,
+        classes=80,
+        autoshape=True,
+        verbose=True,
+    )
+    # model = custom(path='path/to/model.pt')  # custom
+
+    # Images
+    imgs = [
+        "data/images/zidane.jpg",  # filename
+        Path("data/images/zidane.jpg"),  # Path
+        "https://ultralytics.com/images/zidane.jpg",  # URI
+        cv2.imread("data/images/bus.jpg")[:, :, ::-1],  # OpenCV
+        Image.open("data/images/bus.jpg"),  # PIL
+        np.zeros((320, 640, 3)),
+    ]  # numpy
+
+    # Inference
+    results = model(imgs, size=320)  # batched inference
+
+    # Results
+    results.print()
+    results.save()

packages.txt

@@ -0,0 +1,6 @@
+ffmpeg
+libxext6 
+libsm6
+libxrender1
+libfontconfig1
+libice6

planogram.yaml

@@ -0,0 +1,18 @@
+# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
+path: ../planogram_data  # dataset root dir
+train: images/train  # train images (relative to 'path') 128 images
+val: images/val # val images (relative to 'path') 128 images
+test: images/test # test images (optional)
+
+# Classes
+nc: 46  # number of classes
+names: ['Bottle,100PLUS ACTIVE 1.5L','Bottle,100PLUS ACTIVE 500ML','Bottle,100PLUS LEMON LIME 1.5L',
+ 'Bottle,100PLUS ORANGE 500ML', 'Bottle,100PLUS ORIGINAL 1.5L',
+ 'Bottle,100PLUS TANGY ORANGE 1.5L','Bottle,100PLUS ZERO 1.5L', 'Bottle,100PLUS ZERO 500ML','Packet,F:M MAGNOLIA CHOC 1L',
+ 'Bottle,F&N GINGER ADE 1.5L','Bottle,F&N GRAPE 1.5L','Bottle,F&N ICE CREAM SODA 1.5L','Bottle,F&N LYCHEE PEAR 1.5L','Bottle,F&N ORANGE 1.5L',
+ 'Bottle,F&N PINEAPPLE PET 1.5L','Bottle,F&N SARSI 1.5L','Bottle,F&N SS ICE LEM TEA RS 500ML','Bottle,F&N SS ICE LEMON TEA RS 1.5L','Bottle,F&N SS ICE LEMON TEA 1.5L','Bottle,F&N SS ICE LEMON TEA 500ML',
+ 'Bottle,F&N SS ICE PEACH TEA 1.5L','Bottle,SS ICE LEMON GT 1.48L','Bottle,SS WHITE CHRYS TEA 1.48L','Packet,FARMHOUSE FRESH MILK 1L FNDM','Packet,FARMHOUSE PLAIN LF 1L',
+ 'Packet,PURA FRESH MILK 1L FS','Packet,NUTRISOY REG NO SUGAR ADDED 1L','Packet,NUTRISOY PLAIN 475ML','Packet,NUTRISOY PLAIN 1L','Packet,NUTRISOY OMEGA RD SUGAR 1L','Packet,NUTRISOY OMEGA NSA 1L',
+ 'Packet,NUTRISOY ALMOND 1L','Packet,MAGNOLIA FRESH MILK 1L FNDM','Packet,FM MAG FC PLAIN 200ML', 'Packet,MAG OMEGA PLUS PLAIN 200ML','Packet,MAG KURMA MILK 500ML','Packet,MAG KURMA MILK 1L',
+ 'Packet,MAG CHOCOLATE FC 500ML','Packet,MAG BROWN SUGAR SS MILK 1L','Packet,FM MAG LFHC PLN 500ML','Packet,FM MAG LFHC OAT 500ML','Packet,FM MAG LFHC OAT 1L','Packet,FM MAG FC PLAIN 500ML',
+ 'Void,PARTIAL VOID', 'Void,FULL VOID','Bottle,F&N SS ICE LEM TEA 500ML']  # class names

requirements.txt

@@ -38,55 +38,3 @@ pandas>=1.1.4
 # pycocotools>=2.0  # COCO mAP
 # roboflow
 #thop  # FLOPs computation
-
-
-# YOLOv5 requirements
-# Usage: pip install -r requirements.txt
-
-# Base ------------------------------------------------------------------------
-gitpython>=3.1.30
-matplotlib>=3.3
-numpy>=1.23.5
-opencv-python>=4.1.1
-pillow>=10.3.0
-psutil  # system resources
-PyYAML>=5.3.1
-requests>=2.23.0
-scipy>=1.4.1
-thop>=0.1.1  # FLOPs computation
-torch>=1.8.0  # see https://pytorch.org/get-started/locally (recommended)
-torchvision>=0.9.0
-tqdm>=4.64.0
-ultralytics>=8.0.232
-# protobuf<=3.20.1  # https://github.com/ultralytics/yolov5/issues/8012
-
-# Logging ---------------------------------------------------------------------
-# tensorboard>=2.4.1
-# clearml>=1.2.0
-# comet
-
-# Plotting --------------------------------------------------------------------
-pandas>=1.1.4
-seaborn>=0.11.0
-
-# Export ----------------------------------------------------------------------
-# coremltools>=6.0  # CoreML export
-# onnx>=1.10.0  # ONNX export
-# onnx-simplifier>=0.4.1  # ONNX simplifier
-# nvidia-pyindex  # TensorRT export
-# nvidia-tensorrt  # TensorRT export
-# scikit-learn<=1.1.2  # CoreML quantization
-# tensorflow>=2.4.0,<=2.13.1  # TF exports (-cpu, -aarch64, -macos)
-# tensorflowjs>=3.9.0  # TF.js export
-# openvino-dev>=2023.0  # OpenVINO export
-
-# Deploy ----------------------------------------------------------------------
-setuptools>=65.5.1 # Snyk vulnerability fix
-# tritonclient[all]~=2.24.0
-
-# Extras ----------------------------------------------------------------------
-# ipython  # interactive notebook
-# mss  # screenshots
-# albumentations>=1.0.3
-# pycocotools>=2.0.6  # COCO mAP
-wheel>=0.38.0 # not directly required, pinned by Snyk to avoid a vulnerability

runtime.txt

@@ -0,0 +1 @@
+python-3.9.0

setup.sh

@@ -0,0 +1,8 @@
+mkdir -p ~/.streamlit/
+echo "\
+[server]\n\
+headless = true\n\
+port = $PORT\n\
+enableCORS = false\n\
+\n\
+" > ~/.streamlit/config.toml

train.py

@@ -0,0 +1,1046 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Train a YOLOv5 model on a custom dataset
+
+Usage:
+    $ python path/to/train.py --data coco128.yaml --weights yolov5s.pt --img 640
+"""
+
+import argparse
+import logging
+import math
+import os
+import random
+import sys
+import time
+from copy import deepcopy
+from pathlib import Path
+
+import numpy as np
+import torch
+import torch.distributed as dist
+import torch.nn as nn
+import yaml
+from torch.cuda import amp
+from torch.nn.parallel import DistributedDataParallel as DDP
+from torch.optim import SGD, Adam, lr_scheduler
+from tqdm import tqdm
+
+FILE = Path(__file__).absolute()
+sys.path.append(FILE.parents[0].as_posix())  # add yolov5/ to path
+
+import val  # for end-of-epoch mAP
+from models.experimental import attempt_load
+from models.yolo import Model
+from utils.autoanchor import check_anchors
+from utils.callbacks import Callbacks
+from utils.datasets import create_dataloader
+from utils.downloads import attempt_download
+from utils.general import (
+    check_dataset,
+    check_file,
+    check_git_status,
+    check_img_size,
+    check_requirements,
+    check_suffix,
+    check_yaml,
+    colorstr,
+    get_latest_run,
+    increment_path,
+    init_seeds,
+    labels_to_class_weights,
+    labels_to_image_weights,
+    methods,
+    one_cycle,
+    print_mutation,
+    set_logging,
+    strip_optimizer,
+)
+from utils.loggers import Loggers
+from utils.loggers.wandb.wandb_utils import check_wandb_resume
+from utils.loss import ComputeLoss
+from utils.metrics import fitness
+from utils.plots import plot_evolve, plot_labels
+from utils.torch_utils import (
+    EarlyStopping,
+    ModelEMA,
+    de_parallel,
+    intersect_dicts,
+    select_device,
+    torch_distributed_zero_first,
+)
+
+LOGGER = logging.getLogger(__name__)
+LOCAL_RANK = int(
+    os.getenv("LOCAL_RANK", -1)
+)  # https://pytorch.org/docs/stable/elastic/run.html
+RANK = int(os.getenv("RANK", -1))
+WORLD_SIZE = int(os.getenv("WORLD_SIZE", 1))
+
+
+def train(hyp, opt, device, callbacks):  # path/to/hyp.yaml or hyp dictionary
+    (
+        save_dir,
+        epochs,
+        batch_size,
+        weights,
+        single_cls,
+        evolve,
+        data,
+        cfg,
+        resume,
+        noval,
+        nosave,
+        workers,
+        freeze,
+    ) = (
+        Path(opt.save_dir),
+        opt.epochs,
+        opt.batch_size,
+        opt.weights,
+        opt.single_cls,
+        opt.evolve,
+        opt.data,
+        opt.cfg,
+        opt.resume,
+        opt.noval,
+        opt.nosave,
+        opt.workers,
+        opt.freeze,
+    )
+
+    # Directories
+    w = save_dir / "weights"  # weights dir
+    w.mkdir(parents=True, exist_ok=True)  # make dir
+    last, best = w / "last.pt", w / "best.pt"
+
+    # Hyperparameters
+    if isinstance(hyp, str):
+        with open(hyp) as f:
+            hyp = yaml.safe_load(f)  # load hyps dict
+    LOGGER.info(
+        colorstr("hyperparameters: ")
+        + ", ".join(f"{k}={v}" for k, v in hyp.items())
+    )
+
+    # Save run settings
+    with open(save_dir / "hyp.yaml", "w") as f:
+        yaml.safe_dump(hyp, f, sort_keys=False)
+    with open(save_dir / "opt.yaml", "w") as f:
+        yaml.safe_dump(vars(opt), f, sort_keys=False)
+    data_dict = None
+
+    # Loggers
+    if RANK in [-1, 0]:
+        loggers = Loggers(
+            save_dir, weights, opt, hyp, LOGGER
+        )  # loggers instance
+        if loggers.wandb:
+            data_dict = loggers.wandb.data_dict
+            if resume:
+                weights, epochs, hyp = opt.weights, opt.epochs, opt.hyp
+
+        # Register actions
+        for k in methods(loggers):
+            callbacks.register_action(k, callback=getattr(loggers, k))
+
+    # Config
+    plots = not evolve  # create plots
+    cuda = device.type != "cpu"
+    init_seeds(1 + RANK)
+    with torch_distributed_zero_first(RANK):
+        data_dict = data_dict or check_dataset(data)  # check if None
+    train_path, val_path = data_dict["train"], data_dict["val"]
+    nc = 1 if single_cls else int(data_dict["nc"])  # number of classes
+    names = (
+        ["item"]
+        if single_cls and len(data_dict["names"]) != 1
+        else data_dict["names"]
+    )  # class names
+    assert (
+        len(names) == nc
+    ), f"{len(names)} names found for nc={nc} dataset in {data}"  # check
+    is_coco = data.endswith("coco.yaml") and nc == 80  # COCO dataset
+
+    # Model
+    check_suffix(weights, ".pt")  # check weights
+    pretrained = weights.endswith(".pt")
+    if pretrained:
+        with torch_distributed_zero_first(RANK):
+            weights = attempt_download(
+                weights
+            )  # download if not found locally
+        ckpt = torch.load(weights, map_location=device)  # load checkpoint
+        model = Model(
+            cfg or ckpt["model"].yaml, ch=3, nc=nc, anchors=hyp.get("anchors")
+        ).to(
+            device
+        )  # create
+        exclude = (
+            ["anchor"] if (cfg or hyp.get("anchors")) and not resume else []
+        )  # exclude keys
+        csd = (
+            ckpt["model"].float().state_dict()
+        )  # checkpoint state_dict as FP32
+        csd = intersect_dicts(
+            csd, model.state_dict(), exclude=exclude
+        )  # intersect
+        model.load_state_dict(csd, strict=False)  # load
+        LOGGER.info(
+            f"Transferred {len(csd)}/{len(model.state_dict())} items from {weights}"
+        )  # report
+    else:
+        model = Model(cfg, ch=3, nc=nc, anchors=hyp.get("anchors")).to(
+            device
+        )  # create
+
+    # Freeze
+    freeze = [f"model.{x}." for x in range(freeze)]  # layers to freeze
+    for k, v in model.named_parameters():
+        v.requires_grad = True  # train all layers
+        if any(x in k for x in freeze):
+            print(f"freezing {k}")
+            v.requires_grad = False
+
+    # Optimizer
+    nbs = 64  # nominal batch size
+    accumulate = max(
+        round(nbs / batch_size), 1
+    )  # accumulate loss before optimizing
+    hyp["weight_decay"] *= batch_size * accumulate / nbs  # scale weight_decay
+    LOGGER.info(f"Scaled weight_decay = {hyp['weight_decay']}")
+
+    g0, g1, g2 = [], [], []  # optimizer parameter groups
+    for v in model.modules():
+        if hasattr(v, "bias") and isinstance(v.bias, nn.Parameter):  # bias
+            g2.append(v.bias)
+        if isinstance(v, nn.BatchNorm2d):  # weight (no decay)
+            g0.append(v.weight)
+        elif hasattr(v, "weight") and isinstance(
+            v.weight, nn.Parameter
+        ):  # weight (with decay)
+            g1.append(v.weight)
+
+    if opt.adam:
+        optimizer = Adam(
+            g0, lr=hyp["lr0"], betas=(hyp["momentum"], 0.999)
+        )  # adjust beta1 to momentum
+    else:
+        optimizer = SGD(
+            g0, lr=hyp["lr0"], momentum=hyp["momentum"], nesterov=True
+        )
+
+    optimizer.add_param_group(
+        {"params": g1, "weight_decay": hyp["weight_decay"]}
+    )  # add g1 with weight_decay
+    optimizer.add_param_group({"params": g2})  # add g2 (biases)
+    LOGGER.info(
+        f"{colorstr('optimizer:')} {type(optimizer).__name__} with parameter groups "
+        f"{len(g0)} weight, {len(g1)} weight (no decay), {len(g2)} bias"
+    )
+    del g0, g1, g2
+
+    # Scheduler
+    if opt.linear_lr:
+        lf = (
+            lambda x: (1 - x / (epochs - 1)) * (1.0 - hyp["lrf"]) + hyp["lrf"]
+        )  # linear
+    else:
+        lf = one_cycle(1, hyp["lrf"], epochs)  # cosine 1->hyp['lrf']
+    scheduler = lr_scheduler.LambdaLR(
+        optimizer, lr_lambda=lf
+    )  # plot_lr_scheduler(optimizer, scheduler, epochs)
+
+    # EMA
+    ema = ModelEMA(model) if RANK in [-1, 0] else None
+
+    # Resume
+    start_epoch, best_fitness = 0, 0.0
+    if pretrained:
+        # Optimizer
+        if ckpt["optimizer"] is not None:
+            optimizer.load_state_dict(ckpt["optimizer"])
+            best_fitness = ckpt["best_fitness"]
+
+        # EMA
+        if ema and ckpt.get("ema"):
+            ema.ema.load_state_dict(ckpt["ema"].float().state_dict())
+            ema.updates = ckpt["updates"]
+
+        # Epochs
+        start_epoch = ckpt["epoch"] + 1
+        if resume:
+            assert (
+                start_epoch > 0
+            ), f"{weights} training to {epochs} epochs is finished, nothing to resume."
+        if epochs < start_epoch:
+            LOGGER.info(
+                f"{weights} has been trained for {ckpt['epoch']} epochs. Fine-tuning for {epochs} more epochs."
+            )
+            epochs += ckpt["epoch"]  # finetune additional epochs
+
+        del ckpt, csd
+
+    # Image sizes
+    gs = max(int(model.stride.max()), 32)  # grid size (max stride)
+    nl = model.model[
+        -1
+    ].nl  # number of detection layers (used for scaling hyp['obj'])
+    imgsz = check_img_size(
+        opt.imgsz, gs, floor=gs * 2
+    )  # verify imgsz is gs-multiple
+
+    # DP mode
+    if cuda and RANK == -1 and torch.cuda.device_count() > 1:
+        logging.warning(
+            "DP not recommended, instead use torch.distributed.run for best DDP Multi-GPU results.\n"
+            "See Multi-GPU Tutorial at https://github.com/ultralytics/yolov5/issues/475 to get started."
+        )
+        model = torch.nn.DataParallel(model)
+
+    # SyncBatchNorm
+    if opt.sync_bn and cuda and RANK != -1:
+        model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device)
+        LOGGER.info("Using SyncBatchNorm()")
+
+    # Trainloader
+    train_loader, dataset = create_dataloader(
+        train_path,
+        imgsz,
+        batch_size // WORLD_SIZE,
+        gs,
+        single_cls,
+        hyp=hyp,
+        augment=True,
+        cache=opt.cache,
+        rect=opt.rect,
+        rank=RANK,
+        workers=workers,
+        image_weights=opt.image_weights,
+        quad=opt.quad,
+        prefix=colorstr("train: "),
+    )
+    mlc = int(np.concatenate(dataset.labels, 0)[:, 0].max())  # max label class
+    nb = len(train_loader)  # number of batches
+    assert (
+        mlc < nc
+    ), f"Label class {mlc} exceeds nc={nc} in {data}. Possible class labels are 0-{nc - 1}"
+
+    # Process 0
+    if RANK in [-1, 0]:
+        val_loader = create_dataloader(
+            val_path,
+            imgsz,
+            batch_size // WORLD_SIZE * 2,
+            gs,
+            single_cls,
+            hyp=hyp,
+            cache=None if noval else opt.cache,
+            rect=True,
+            rank=-1,
+            workers=workers,
+            pad=0.5,
+            prefix=colorstr("val: "),
+        )[0]
+
+        if not resume:
+            labels = np.concatenate(dataset.labels, 0)
+            # c = torch.tensor(labels[:, 0])  # classes
+            # cf = torch.bincount(c.long(), minlength=nc) + 1.  # frequency
+            # model._initialize_biases(cf.to(device))
+            if plots:
+                plot_labels(labels, names, save_dir)
+
+            # Anchors
+            if not opt.noautoanchor:
+                check_anchors(
+                    dataset, model=model, thr=hyp["anchor_t"], imgsz=imgsz
+                )
+            model.half().float()  # pre-reduce anchor precision
+
+        callbacks.run("on_pretrain_routine_end")
+
+    # DDP mode
+    if cuda and RANK != -1:
+        model = DDP(model, device_ids=[LOCAL_RANK], output_device=LOCAL_RANK)
+
+    # Model parameters
+    hyp["box"] *= 3.0 / nl  # scale to layers
+    hyp["cls"] *= nc / 80.0 * 3.0 / nl  # scale to classes and layers
+    hyp["obj"] *= (
+        (imgsz / 640) ** 2 * 3.0 / nl
+    )  # scale to image size and layers
+    hyp["label_smoothing"] = opt.label_smoothing
+    model.nc = nc  # attach number of classes to model
+    model.hyp = hyp  # attach hyperparameters to model
+    model.class_weights = (
+        labels_to_class_weights(dataset.labels, nc).to(device) * nc
+    )  # attach class weights
+    model.names = names
+
+    # Start training
+    t0 = time.time()
+    nw = max(
+        round(hyp["warmup_epochs"] * nb), 1000
+    )  # number of warmup iterations, max(3 epochs, 1k iterations)
+    # nw = min(nw, (epochs - start_epoch) / 2 * nb)  # limit warmup to < 1/2 of training
+    last_opt_step = -1
+    maps = np.zeros(nc)  # mAP per class
+    results = (
+        0,
+        0,
+        0,
+        0,
+        0,
+        0,
+        0,
+    )  # P, R, [email protected], [email protected], val_loss(box, obj, cls)
+    scheduler.last_epoch = start_epoch - 1  # do not move
+    scaler = amp.GradScaler(enabled=cuda)
+    stopper = EarlyStopping(patience=opt.patience)
+    compute_loss = ComputeLoss(model)  # init loss class
+    LOGGER.info(
+        f"Image sizes {imgsz} train, {imgsz} val\n"
+        f"Using {train_loader.num_workers} dataloader workers\n"
+        f"Logging results to {colorstr('bold', save_dir)}\n"
+        f"Starting training for {epochs} epochs..."
+    )
+    for epoch in range(
+        start_epoch, epochs
+    ):  # epoch ------------------------------------------------------------------
+        model.train()
+
+        # Update image weights (optional, single-GPU only)
+        if opt.image_weights:
+            cw = (
+                model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc
+            )  # class weights
+            iw = labels_to_image_weights(
+                dataset.labels, nc=nc, class_weights=cw
+            )  # image weights
+            dataset.indices = random.choices(
+                range(dataset.n), weights=iw, k=dataset.n
+            )  # rand weighted idx
+
+        # Update mosaic border (optional)
+        # b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs)
+        # dataset.mosaic_border = [b - imgsz, -b]  # height, width borders
+
+        mloss = torch.zeros(3, device=device)  # mean losses
+        if RANK != -1:
+            train_loader.sampler.set_epoch(epoch)
+        pbar = enumerate(train_loader)
+        LOGGER.info(
+            ("\n" + "%10s" * 7)
+            % ("Epoch", "gpu_mem", "box", "obj", "cls", "labels", "img_size")
+        )
+        if RANK in [-1, 0]:
+            pbar = tqdm(pbar, total=nb)  # progress bar
+        optimizer.zero_grad()
+        for i, (
+            imgs,
+            targets,
+            paths,
+            _,
+        ) in (
+            pbar
+        ):  # batch -------------------------------------------------------------
+            ni = (
+                i + nb * epoch
+            )  # number integrated batches (since train start)
+            imgs = (
+                imgs.to(device, non_blocking=True).float() / 255.0
+            )  # uint8 to float32, 0-255 to 0.0-1.0
+
+            # Warmup
+            if ni <= nw:
+                xi = [0, nw]  # x interp
+                # compute_loss.gr = np.interp(ni, xi, [0.0, 1.0])  # iou loss ratio (obj_loss = 1.0 or iou)
+                accumulate = max(
+                    1, np.interp(ni, xi, [1, nbs / batch_size]).round()
+                )
+                for j, x in enumerate(optimizer.param_groups):
+                    # bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
+                    x["lr"] = np.interp(
+                        ni,
+                        xi,
+                        [
+                            hyp["warmup_bias_lr"] if j == 2 else 0.0,
+                            x["initial_lr"] * lf(epoch),
+                        ],
+                    )
+                    if "momentum" in x:
+                        x["momentum"] = np.interp(
+                            ni, xi, [hyp["warmup_momentum"], hyp["momentum"]]
+                        )
+
+            # Multi-scale
+            if opt.multi_scale:
+                sz = (
+                    random.randrange(imgsz * 0.5, imgsz * 1.5 + gs) // gs * gs
+                )  # size
+                sf = sz / max(imgs.shape[2:])  # scale factor
+                if sf != 1:
+                    ns = [
+                        math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]
+                    ]  # new shape (stretched to gs-multiple)
+                    imgs = nn.functional.interpolate(
+                        imgs, size=ns, mode="bilinear", align_corners=False
+                    )
+
+            # Forward
+            with amp.autocast(enabled=cuda):
+                pred = model(imgs)  # forward
+                loss, loss_items = compute_loss(
+                    pred, targets.to(device)
+                )  # loss scaled by batch_size
+                if RANK != -1:
+                    loss *= WORLD_SIZE  # gradient averaged between devices in DDP mode
+                if opt.quad:
+                    loss *= 4.0
+
+            # Backward
+            scaler.scale(loss).backward()
+
+            # Optimize
+            if ni - last_opt_step >= accumulate:
+                scaler.step(optimizer)  # optimizer.step
+                scaler.update()
+                optimizer.zero_grad()
+                if ema:
+                    ema.update(model)
+                last_opt_step = ni
+
+            # Log
+            if RANK in [-1, 0]:
+                mloss = (mloss * i + loss_items) / (
+                    i + 1
+                )  # update mean losses
+                mem = f"{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G"  # (GB)
+                pbar.set_description(
+                    ("%10s" * 2 + "%10.4g" * 5)
+                    % (
+                        f"{epoch}/{epochs - 1}",
+                        mem,
+                        *mloss,
+                        targets.shape[0],
+                        imgs.shape[-1],
+                    )
+                )
+                callbacks.run(
+                    "on_train_batch_end",
+                    ni,
+                    model,
+                    imgs,
+                    targets,
+                    paths,
+                    plots,
+                    opt.sync_bn,
+                )
+            # end batch ------------------------------------------------------------------------------------------------
+
+        # Scheduler
+        lr = [x["lr"] for x in optimizer.param_groups]  # for loggers
+        scheduler.step()
+
+        if RANK in [-1, 0]:
+            # mAP
+            callbacks.run("on_train_epoch_end", epoch=epoch)
+            ema.update_attr(
+                model,
+                include=[
+                    "yaml",
+                    "nc",
+                    "hyp",
+                    "names",
+                    "stride",
+                    "class_weights",
+                ],
+            )
+            final_epoch = (epoch + 1 == epochs) or stopper.possible_stop
+            if not noval or final_epoch:  # Calculate mAP
+                results, maps, _ = val.run(
+                    data_dict,
+                    batch_size=batch_size // WORLD_SIZE * 2,
+                    imgsz=imgsz,
+                    model=ema.ema,
+                    single_cls=single_cls,
+                    dataloader=val_loader,
+                    save_dir=save_dir,
+                    save_json=is_coco and final_epoch,
+                    verbose=nc < 50 and final_epoch,
+                    plots=plots and final_epoch,
+                    callbacks=callbacks,
+                    compute_loss=compute_loss,
+                )
+
+            # Update best mAP
+            fi = fitness(
+                np.array(results).reshape(1, -1)
+            )  # weighted combination of [P, R, [email protected], [email protected]]
+            if fi > best_fitness:
+                best_fitness = fi
+            log_vals = list(mloss) + list(results) + lr
+            callbacks.run(
+                "on_fit_epoch_end", log_vals, epoch, best_fitness, fi
+            )
+
+            # Save model
+            if (not nosave) or (final_epoch and not evolve):  # if save
+                ckpt = {
+                    "epoch": epoch,
+                    "best_fitness": best_fitness,
+                    "model": deepcopy(de_parallel(model)).half(),
+                    "ema": deepcopy(ema.ema).half(),
+                    "updates": ema.updates,
+                    "optimizer": optimizer.state_dict(),
+                    "wandb_id": loggers.wandb.wandb_run.id
+                    if loggers.wandb
+                    else None,
+                }
+
+                # Save last, best and delete
+                torch.save(ckpt, last)
+                if best_fitness == fi:
+                    torch.save(ckpt, best)
+                del ckpt
+                callbacks.run(
+                    "on_model_save", last, epoch, final_epoch, best_fitness, fi
+                )
+
+            # Stop Single-GPU
+            if RANK == -1 and stopper(epoch=epoch, fitness=fi):
+                break
+
+            # Stop DDP TODO: known issues shttps://github.com/ultralytics/yolov5/pull/4576
+            # stop = stopper(epoch=epoch, fitness=fi)
+            # if RANK == 0:
+            #    dist.broadcast_object_list([stop], 0)  # broadcast 'stop' to all ranks
+
+        # Stop DPP
+        # with torch_distributed_zero_first(RANK):
+        # if stop:
+        #    break  # must break all DDP ranks
+
+        # end epoch ----------------------------------------------------------------------------------------------------
+    # end training -----------------------------------------------------------------------------------------------------
+    if RANK in [-1, 0]:
+        LOGGER.info(
+            f"\n{epoch - start_epoch + 1} epochs completed in {(time.time() - t0) / 3600:.3f} hours."
+        )
+        if not evolve:
+            if is_coco:  # COCO dataset
+                for m in (
+                    [last, best] if best.exists() else [last]
+                ):  # speed, mAP tests
+                    results, _, _ = val.run(
+                        data_dict,
+                        batch_size=batch_size // WORLD_SIZE * 2,
+                        imgsz=imgsz,
+                        model=attempt_load(m, device).half(),
+                        iou_thres=0.7,  # NMS IoU threshold for best pycocotools results
+                        single_cls=single_cls,
+                        dataloader=val_loader,
+                        save_dir=save_dir,
+                        save_json=True,
+                        plots=False,
+                    )
+            # Strip optimizers
+            for f in last, best:
+                if f.exists():
+                    strip_optimizer(f)  # strip optimizers
+        callbacks.run("on_train_end", last, best, plots, epoch)
+        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}")
+
+    torch.cuda.empty_cache()
+    return results
+
+
+def parse_opt(known=False):
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--weights",
+        type=str,
+        default="yolov5s.pt",
+        help="initial weights path",
+    )
+    parser.add_argument("--cfg", type=str, default="", help="model.yaml path")
+    parser.add_argument(
+        "--data",
+        type=str,
+        default="data/coco128.yaml",
+        help="dataset.yaml path",
+    )
+    parser.add_argument(
+        "--hyp",
+        type=str,
+        default="data/hyps/hyp.scratch.yaml",
+        help="hyperparameters path",
+    )
+    parser.add_argument("--epochs", type=int, default=300)
+    parser.add_argument(
+        "--batch-size",
+        type=int,
+        default=16,
+        help="total batch size for all GPUs",
+    )
+    parser.add_argument(
+        "--imgsz",
+        "--img",
+        "--img-size",
+        type=int,
+        default=640,
+        help="train, val image size (pixels)",
+    )
+    parser.add_argument(
+        "--rect", action="store_true", help="rectangular training"
+    )
+    parser.add_argument(
+        "--resume",
+        nargs="?",
+        const=True,
+        default=False,
+        help="resume most recent training",
+    )
+    parser.add_argument(
+        "--nosave", action="store_true", help="only save final checkpoint"
+    )
+    parser.add_argument(
+        "--noval", action="store_true", help="only validate final epoch"
+    )
+    parser.add_argument(
+        "--noautoanchor", action="store_true", help="disable autoanchor check"
+    )
+    parser.add_argument(
+        "--evolve",
+        type=int,
+        nargs="?",
+        const=300,
+        help="evolve hyperparameters for x generations",
+    )
+    parser.add_argument("--bucket", type=str, default="", help="gsutil bucket")
+    parser.add_argument(
+        "--cache",
+        type=str,
+        nargs="?",
+        const="ram",
+        help='--cache images in "ram" (default) or "disk"',
+    )
+    parser.add_argument(
+        "--image-weights",
+        action="store_true",
+        help="use weighted image selection for training",
+    )
+    parser.add_argument(
+        "--device", default="", help="cuda device, i.e. 0 or 0,1,2,3 or cpu"
+    )
+    parser.add_argument(
+        "--multi-scale", action="store_true", help="vary img-size +/- 50%%"
+    )
+    parser.add_argument(
+        "--single-cls",
+        action="store_true",
+        help="train multi-class data as single-class",
+    )
+    parser.add_argument(
+        "--adam", action="store_true", help="use torch.optim.Adam() optimizer"
+    )
+    parser.add_argument(
+        "--sync-bn",
+        action="store_true",
+        help="use SyncBatchNorm, only available in DDP mode",
+    )
+    parser.add_argument(
+        "--workers",
+        type=int,
+        default=8,
+        help="maximum number of dataloader workers",
+    )
+    parser.add_argument(
+        "--project", default="runs/train", help="save to project/name"
+    )
+    parser.add_argument("--entity", default=None, help="W&B entity")
+    parser.add_argument("--name", default="exp", help="save to project/name")
+    parser.add_argument(
+        "--exist-ok",
+        action="store_true",
+        help="existing project/name ok, do not increment",
+    )
+    parser.add_argument("--quad", action="store_true", help="quad dataloader")
+    parser.add_argument("--linear-lr", action="store_true", help="linear LR")
+    parser.add_argument(
+        "--label-smoothing",
+        type=float,
+        default=0.0,
+        help="Label smoothing epsilon",
+    )
+    parser.add_argument(
+        "--upload_dataset",
+        action="store_true",
+        help="Upload dataset as W&B artifact table",
+    )
+    parser.add_argument(
+        "--bbox_interval",
+        type=int,
+        default=-1,
+        help="Set bounding-box image logging interval for W&B",
+    )
+    parser.add_argument(
+        "--save_period",
+        type=int,
+        default=-1,
+        help='Log model after every "save_period" epoch',
+    )
+    parser.add_argument(
+        "--artifact_alias",
+        type=str,
+        default="latest",
+        help="version of dataset artifact to be used",
+    )
+    parser.add_argument(
+        "--local_rank",
+        type=int,
+        default=-1,
+        help="DDP parameter, do not modify",
+    )
+    parser.add_argument(
+        "--freeze",
+        type=int,
+        default=0,
+        help="Number of layers to freeze. backbone=10, all=24",
+    )
+    parser.add_argument(
+        "--patience",
+        type=int,
+        default=100,
+        help="EarlyStopping patience (epochs without improvement)",
+    )
+    opt = parser.parse_known_args()[0] if known else parser.parse_args()
+    return opt
+
+
+def main(opt, callbacks=Callbacks()):
+    # Checks
+    set_logging(RANK)
+    if RANK in [-1, 0]:
+        print(
+            colorstr("train: ")
+            + ", ".join(f"{k}={v}" for k, v in vars(opt).items())
+        )
+        check_git_status()
+        check_requirements(
+            requirements=FILE.parent / "requirements.txt", exclude=["thop"]
+        )
+
+    # Resume
+    if (
+        opt.resume and not check_wandb_resume(opt) and not opt.evolve
+    ):  # resume an interrupted run
+        ckpt = (
+            opt.resume if isinstance(opt.resume, str) else get_latest_run()
+        )  # specified or most recent path
+        assert os.path.isfile(
+            ckpt
+        ), "ERROR: --resume checkpoint does not exist"
+        with open(Path(ckpt).parent.parent / "opt.yaml") as f:
+            opt = argparse.Namespace(**yaml.safe_load(f))  # replace
+        opt.cfg, opt.weights, opt.resume = "", ckpt, True  # reinstate
+        LOGGER.info(f"Resuming training from {ckpt}")
+    else:
+        opt.data, opt.cfg, opt.hyp = (
+            check_file(opt.data),
+            check_yaml(opt.cfg),
+            check_yaml(opt.hyp),
+        )  # check YAMLs
+        assert len(opt.cfg) or len(
+            opt.weights
+        ), "either --cfg or --weights must be specified"
+        if opt.evolve:
+            opt.project = "runs/evolve"
+            opt.exist_ok = opt.resume
+        opt.save_dir = str(
+            increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)
+        )
+
+    # DDP mode
+    device = select_device(opt.device, batch_size=opt.batch_size)
+    if LOCAL_RANK != -1:
+        from datetime import timedelta
+
+        assert (
+            torch.cuda.device_count() > LOCAL_RANK
+        ), "insufficient CUDA devices for DDP command"
+        assert (
+            opt.batch_size % WORLD_SIZE == 0
+        ), "--batch-size must be multiple of CUDA device count"
+        assert (
+            not opt.image_weights
+        ), "--image-weights argument is not compatible with DDP training"
+        assert (
+            not opt.evolve
+        ), "--evolve argument is not compatible with DDP training"
+        torch.cuda.set_device(LOCAL_RANK)
+        device = torch.device("cuda", LOCAL_RANK)
+        dist.init_process_group(
+            backend="nccl" if dist.is_nccl_available() else "gloo"
+        )
+
+    # Train
+    if not opt.evolve:
+        train(opt.hyp, opt, device, callbacks)
+        if WORLD_SIZE > 1 and RANK == 0:
+            _ = [
+                print("Destroying process group... ", end=""),
+                dist.destroy_process_group(),
+                print("Done."),
+            ]
+
+    # Evolve hyperparameters (optional)
+    else:
+        # Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit)
+        meta = {
+            "lr0": (
+                1,
+                1e-5,
+                1e-1,
+            ),  # initial learning rate (SGD=1E-2, Adam=1E-3)
+            "lrf": (
+                1,
+                0.01,
+                1.0,
+            ),  # final OneCycleLR learning rate (lr0 * lrf)
+            "momentum": (0.3, 0.6, 0.98),  # SGD momentum/Adam beta1
+            "weight_decay": (1, 0.0, 0.001),  # optimizer weight decay
+            "warmup_epochs": (1, 0.0, 5.0),  # warmup epochs (fractions ok)
+            "warmup_momentum": (1, 0.0, 0.95),  # warmup initial momentum
+            "warmup_bias_lr": (1, 0.0, 0.2),  # warmup initial bias lr
+            "box": (1, 0.02, 0.2),  # box loss gain
+            "cls": (1, 0.2, 4.0),  # cls loss gain
+            "cls_pw": (1, 0.5, 2.0),  # cls BCELoss positive_weight
+            "obj": (1, 0.2, 4.0),  # obj loss gain (scale with pixels)
+            "obj_pw": (1, 0.5, 2.0),  # obj BCELoss positive_weight
+            "iou_t": (0, 0.1, 0.7),  # IoU training threshold
+            "anchor_t": (1, 2.0, 8.0),  # anchor-multiple threshold
+            "anchors": (2, 2.0, 10.0),  # anchors per output grid (0 to ignore)
+            "fl_gamma": (
+                0,
+                0.0,
+                2.0,
+            ),  # focal loss gamma (efficientDet default gamma=1.5)
+            "hsv_h": (1, 0.0, 0.1),  # image HSV-Hue augmentation (fraction)
+            "hsv_s": (
+                1,
+                0.0,
+                0.9,
+            ),  # image HSV-Saturation augmentation (fraction)
+            "hsv_v": (1, 0.0, 0.9),  # image HSV-Value augmentation (fraction)
+            "degrees": (1, 0.0, 45.0),  # image rotation (+/- deg)
+            "translate": (1, 0.0, 0.9),  # image translation (+/- fraction)
+            "scale": (1, 0.0, 0.9),  # image scale (+/- gain)
+            "shear": (1, 0.0, 10.0),  # image shear (+/- deg)
+            "perspective": (
+                0,
+                0.0,
+                0.001,
+            ),  # image perspective (+/- fraction), range 0-0.001
+            "flipud": (1, 0.0, 1.0),  # image flip up-down (probability)
+            "fliplr": (0, 0.0, 1.0),  # image flip left-right (probability)
+            "mosaic": (1, 0.0, 1.0),  # image mixup (probability)
+            "mixup": (1, 0.0, 1.0),  # image mixup (probability)
+            "copy_paste": (1, 0.0, 1.0),
+        }  # segment copy-paste (probability)
+
+        with open(opt.hyp) as f:
+            hyp = yaml.safe_load(f)  # load hyps dict
+            if "anchors" not in hyp:  # anchors commented in hyp.yaml
+                hyp["anchors"] = 3
+        opt.noval, opt.nosave, save_dir = (
+            True,
+            True,
+            Path(opt.save_dir),
+        )  # only val/save final epoch
+        # ei = [isinstance(x, (int, float)) for x in hyp.values()]  # evolvable indices
+        evolve_yaml, evolve_csv = (
+            save_dir / "hyp_evolve.yaml",
+            save_dir / "evolve.csv",
+        )
+        if opt.bucket:
+            os.system(
+                f"gsutil cp gs://{opt.bucket}/evolve.csv {save_dir}"
+            )  # download evolve.csv if exists
+
+        for _ in range(opt.evolve):  # generations to evolve
+            if (
+                evolve_csv.exists()
+            ):  # if evolve.csv exists: select best hyps and mutate
+                # Select parent(s)
+                parent = (
+                    "single"  # parent selection method: 'single' or 'weighted'
+                )
+                x = np.loadtxt(evolve_csv, ndmin=2, delimiter=",", skiprows=1)
+                n = min(5, len(x))  # number of previous results to consider
+                x = x[np.argsort(-fitness(x))][:n]  # top n mutations
+                w = fitness(x) - fitness(x).min() + 1e-6  # weights (sum > 0)
+                if parent == "single" or len(x) == 1:
+                    # x = x[random.randint(0, n - 1)]  # random selection
+                    x = x[
+                        random.choices(range(n), weights=w)[0]
+                    ]  # weighted selection
+                elif parent == "weighted":
+                    x = (x * w.reshape(n, 1)).sum(
+                        0
+                    ) / w.sum()  # weighted combination
+
+                # Mutate
+                mp, s = 0.8, 0.2  # mutation probability, sigma
+                npr = np.random
+                npr.seed(int(time.time()))
+                g = np.array([meta[k][0] for k in hyp.keys()])  # gains 0-1
+                ng = len(meta)
+                v = np.ones(ng)
+                while all(
+                    v == 1
+                ):  # mutate until a change occurs (prevent duplicates)
+                    v = (
+                        g
+                        * (npr.random(ng) < mp)
+                        * npr.randn(ng)
+                        * npr.random()
+                        * s
+                        + 1
+                    ).clip(0.3, 3.0)
+                for i, k in enumerate(hyp.keys()):  # plt.hist(v.ravel(), 300)
+                    hyp[k] = float(x[i + 7] * v[i])  # mutate
+
+            # Constrain to limits
+            for k, v in meta.items():
+                hyp[k] = max(hyp[k], v[1])  # lower limit
+                hyp[k] = min(hyp[k], v[2])  # upper limit
+                hyp[k] = round(hyp[k], 5)  # significant digits
+
+            # Train mutation
+            results = train(hyp.copy(), opt, device, callbacks)
+
+            # Write mutation results
+            print_mutation(results, hyp.copy(), save_dir, opt.bucket)
+
+        # Plot results
+        plot_evolve(evolve_csv)
+        print(
+            f"Hyperparameter evolution finished\n"
+            f"Results saved to {colorstr('bold', save_dir)}\n"
+            f"Use best hyperparameters example: $ python train.py --hyp {evolve_yaml}"
+        )
+
+
+def run(**kwargs):
+    # Usage: import train; train.run(data='coco128.yaml', imgsz=320, weights='yolov5m.pt')
+    opt = parse_opt(True)
+    for k, v in kwargs.items():
+        setattr(opt, k, v)
+    main(opt)
+
+
+if __name__ == "__main__":
+    opt = parse_opt()
+    main(opt)

tutorial.ipynb

@@ -0,0 +1,1022 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "YOLOv5 Tutorial",
+      "provenance": [],
+      "collapsed_sections": [],
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "accelerator": "GPU",
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "484511f272e64eab8b42e68dac5f7a66": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "HBoxView",
+            "_dom_classes": [],
+            "_model_name": "HBoxModel",
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "box_style": "",
+            "layout": "IPY_MODEL_78cceec059784f2bb36988d3336e4d56",
+            "_model_module": "@jupyter-widgets/controls",
+            "children": [
+              "IPY_MODEL_ab93d8b65c134605934ff9ec5efb1bb6",
+              "IPY_MODEL_30df865ded4c434191bce772c9a82f3a",
+              "IPY_MODEL_20cdc61eb3404f42a12b37901b0d85fb"
+            ]
+          }
+        },
+        "78cceec059784f2bb36988d3336e4d56": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "ab93d8b65c134605934ff9ec5efb1bb6": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "HTMLView",
+            "style": "IPY_MODEL_2d7239993a9645b09b221405ac682743",
+            "_dom_classes": [],
+            "description": "",
+            "_model_name": "HTMLModel",
+            "placeholder": "​",
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "value": "100%",
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "description_tooltip": null,
+            "_model_module": "@jupyter-widgets/controls",
+            "layout": "IPY_MODEL_17b5a87f92104ec7ab96bf507637d0d2"
+          }
+        },
+        "30df865ded4c434191bce772c9a82f3a": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "ProgressView",
+            "style": "IPY_MODEL_2358bfb2270247359e94b066b3cc3d1f",
+            "_dom_classes": [],
+            "description": "",
+            "_model_name": "FloatProgressModel",
+            "bar_style": "success",
+            "max": 818322941,
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "value": 818322941,
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "orientation": "horizontal",
+            "min": 0,
+            "description_tooltip": null,
+            "_model_module": "@jupyter-widgets/controls",
+            "layout": "IPY_MODEL_3e984405db654b0b83b88b2db08baffd"
+          }
+        },
+        "20cdc61eb3404f42a12b37901b0d85fb": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "HTMLView",
+            "style": "IPY_MODEL_654d8a19b9f949c6bbdaf8b0875c931e",
+            "_dom_classes": [],
+            "description": "",
+            "_model_name": "HTMLModel",
+            "placeholder": "​",
+            "_view_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "value": " 780M/780M [00:33<00:00, 24.4MB/s]",
+            "_view_count": null,
+            "_view_module_version": "1.5.0",
+            "description_tooltip": null,
+            "_model_module": "@jupyter-widgets/controls",
+            "layout": "IPY_MODEL_896030c5d13b415aaa05032818d81a6e"
+          }
+        },
+        "2d7239993a9645b09b221405ac682743": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "StyleView",
+            "_model_name": "DescriptionStyleModel",
+            "description_width": "",
+            "_view_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.2.0",
+            "_model_module": "@jupyter-widgets/controls"
+          }
+        },
+        "17b5a87f92104ec7ab96bf507637d0d2": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "2358bfb2270247359e94b066b3cc3d1f": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "StyleView",
+            "_model_name": "ProgressStyleModel",
+            "description_width": "",
+            "_view_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.2.0",
+            "bar_color": null,
+            "_model_module": "@jupyter-widgets/controls"
+          }
+        },
+        "3e984405db654b0b83b88b2db08baffd": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        },
+        "654d8a19b9f949c6bbdaf8b0875c931e": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_view_name": "StyleView",
+            "_model_name": "DescriptionStyleModel",
+            "description_width": "",
+            "_view_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.5.0",
+            "_view_count": null,
+            "_view_module_version": "1.2.0",
+            "_model_module": "@jupyter-widgets/controls"
+          }
+        },
+        "896030c5d13b415aaa05032818d81a6e": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_view_name": "LayoutView",
+            "grid_template_rows": null,
+            "right": null,
+            "justify_content": null,
+            "_view_module": "@jupyter-widgets/base",
+            "overflow": null,
+            "_model_module_version": "1.2.0",
+            "_view_count": null,
+            "flex_flow": null,
+            "width": null,
+            "min_width": null,
+            "border": null,
+            "align_items": null,
+            "bottom": null,
+            "_model_module": "@jupyter-widgets/base",
+            "top": null,
+            "grid_column": null,
+            "overflow_y": null,
+            "overflow_x": null,
+            "grid_auto_flow": null,
+            "grid_area": null,
+            "grid_template_columns": null,
+            "flex": null,
+            "_model_name": "LayoutModel",
+            "justify_items": null,
+            "grid_row": null,
+            "max_height": null,
+            "align_content": null,
+            "visibility": null,
+            "align_self": null,
+            "height": null,
+            "min_height": null,
+            "padding": null,
+            "grid_auto_rows": null,
+            "grid_gap": null,
+            "max_width": null,
+            "order": null,
+            "_view_module_version": "1.2.0",
+            "grid_template_areas": null,
+            "object_position": null,
+            "object_fit": null,
+            "grid_auto_columns": null,
+            "margin": null,
+            "display": null,
+            "left": null
+          }
+        }
+      }
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "t6MPjfT5NrKQ"
+      },
+      "source": [
+        "<a align=\"left\" href=\"https://ultralytics.com/yolov5\" target=\"_blank\">\n",
+        "<img src=\"https://user-images.githubusercontent.com/26833433/125273437-35b3fc00-e30d-11eb-9079-46f313325424.png\"></a>\n",
+        "\n",
+        "This is the **official YOLOv5 🚀 notebook** by **Ultralytics**, and is freely available for redistribution under the [GPL-3.0 license](https://choosealicense.com/licenses/gpl-3.0/). \n",
+        "For more information please visit https://github.com/ultralytics/yolov5 and https://ultralytics.com. Thank you!"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "7mGmQbAO5pQb"
+      },
+      "source": [
+        "# Setup\n",
+        "\n",
+        "Clone repo, install dependencies and check PyTorch and GPU."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "wbvMlHd_QwMG",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "4d67116a-43e9-4d84-d19e-1edd83f23a04"
+      },
+      "source": [
+        "!git clone https://github.com/ultralytics/yolov5  # clone repo\n",
+        "%cd yolov5\n",
+        "%pip install -qr requirements.txt  # install dependencies\n",
+        "\n",
+        "import torch\n",
+        "from IPython.display import Image, clear_output  # to display images\n",
+        "\n",
+        "clear_output()\n",
+        "print(f\"Setup complete. Using torch {torch.__version__} ({torch.cuda.get_device_properties(0).name if torch.cuda.is_available() else 'CPU'})\")"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "Setup complete. Using torch 1.9.0+cu102 (Tesla V100-SXM2-16GB)\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4JnkELT0cIJg"
+      },
+      "source": [
+        "# 1. Inference\n",
+        "\n",
+        "`detect.py` runs YOLOv5 inference on a variety of sources, downloading models automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases), and saving results to `runs/detect`. Example inference sources are:\n",
+        "\n",
+        "```shell\n",
+        "python detect.py --source 0  # webcam\n",
+        "                          file.jpg  # image \n",
+        "                          file.mp4  # video\n",
+        "                          path/  # directory\n",
+        "                          path/*.jpg  # glob\n",
+        "                          'https://youtu.be/NUsoVlDFqZg'  # YouTube\n",
+        "                          'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "zR9ZbuQCH7FX",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "8b728908-81ab-4861-edb0-4d0c46c439fb"
+      },
+      "source": [
+        "!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images/\n",
+        "Image(filename='runs/detect/exp/zidane.jpg', width=600)"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov5s.pt'], source=data/images/, imgsz=640, conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False\n",
+            "YOLOv5 🚀 v5.0-367-g01cdb76 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",
+            "\n",
+            "Fusing layers... \n",
+            "Model Summary: 224 layers, 7266973 parameters, 0 gradients\n",
+            "image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 1 fire hydrant, Done. (0.007s)\n",
+            "image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.007s)\n",
+            "Results saved to \u001b[1mruns/detect/exp\u001b[0m\n",
+            "Done. (0.091s)\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "hkAzDWJ7cWTr"
+      },
+      "source": [
+        "&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\n",
+        "<img align=\"left\" src=\"https://user-images.githubusercontent.com/26833433/127574988-6a558aa1-d268-44b9-bf6b-62d4c605cc72.jpg\" width=\"600\">"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0eq1SMWl6Sfn"
+      },
+      "source": [
+        "# 2. Validate\n",
+        "Validate a model's accuracy on [COCO](https://cocodataset.org/#home) val or test-dev datasets. Models are downloaded automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases). To show results by class use the `--verbose` flag. Note that `pycocotools` metrics may be ~1% better than the equivalent repo metrics, as is visible below, due to slight differences in mAP computation."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "eyTZYGgRjnMc"
+      },
+      "source": [
+        "## COCO val2017\n",
+        "Download [COCO val 2017](https://github.com/ultralytics/yolov5/blob/74b34872fdf41941cddcf243951cdb090fbac17b/data/coco.yaml#L14) dataset (1GB - 5000 images), and test model accuracy."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "WQPtK1QYVaD_",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 48,
+          "referenced_widgets": [
+            "484511f272e64eab8b42e68dac5f7a66",
+            "78cceec059784f2bb36988d3336e4d56",
+            "ab93d8b65c134605934ff9ec5efb1bb6",
+            "30df865ded4c434191bce772c9a82f3a",
+            "20cdc61eb3404f42a12b37901b0d85fb",
+            "2d7239993a9645b09b221405ac682743",
+            "17b5a87f92104ec7ab96bf507637d0d2",
+            "2358bfb2270247359e94b066b3cc3d1f",
+            "3e984405db654b0b83b88b2db08baffd",
+            "654d8a19b9f949c6bbdaf8b0875c931e",
+            "896030c5d13b415aaa05032818d81a6e"
+          ]
+        },
+        "outputId": "7e6f5c96-c819-43e1-cd03-d3b9878cf8de"
+      },
+      "source": [
+        "# Download COCO val2017\n",
+        "torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017val.zip', 'tmp.zip')\n",
+        "!unzip -q tmp.zip -d ../datasets && rm tmp.zip"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "484511f272e64eab8b42e68dac5f7a66",
+              "version_minor": 0,
+              "version_major": 2
+            },
+            "text/plain": [
+              "  0%|          | 0.00/780M [00:00<?, ?B/s]"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          }
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "X58w8JLpMnjH",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "3dd0e2fc-aecf-4108-91b1-6392da1863cb"
+      },
+      "source": [
+        "# Run YOLOv5x on COCO val2017\n",
+        "!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "\u001b[34m\u001b[1mval: \u001b[0mdata=./data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, task=val, device=, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True\n",
+            "YOLOv5 🚀 v5.0-367-g01cdb76 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",
+            "\n",
+            "Downloading https://github.com/ultralytics/yolov5/releases/download/v5.0/yolov5x.pt to yolov5x.pt...\n",
+            "100% 168M/168M [00:08<00:00, 20.6MB/s]\n",
+            "\n",
+            "Fusing layers... \n",
+            "Model Summary: 476 layers, 87730285 parameters, 0 gradients\n",
+            "\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:01<00:00, 2749.96it/s]\n",
+            "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: ../datasets/coco/val2017.cache\n",
+            "               Class     Images     Labels          P          R     [email protected] [email protected]:.95: 100% 157/157 [01:08<00:00,  2.28it/s]\n",
+            "                 all       5000      36335      0.746      0.626       0.68       0.49\n",
+            "Speed: 0.1ms pre-process, 5.1ms inference, 1.6ms NMS per image at shape (32, 3, 640, 640)\n",
+            "\n",
+            "Evaluating pycocotools mAP... saving runs/val/exp/yolov5x_predictions.json...\n",
+            "loading annotations into memory...\n",
+            "Done (t=0.46s)\n",
+            "creating index...\n",
+            "index created!\n",
+            "Loading and preparing results...\n",
+            "DONE (t=4.94s)\n",
+            "creating index...\n",
+            "index created!\n",
+            "Running per image evaluation...\n",
+            "Evaluate annotation type *bbox*\n",
+            "DONE (t=83.60s).\n",
+            "Accumulating evaluation results...\n",
+            "DONE (t=13.22s).\n",
+            " Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.504\n",
+            " Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.688\n",
+            " Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.546\n",
+            " Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.351\n",
+            " Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.551\n",
+            " Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.644\n",
+            " Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.382\n",
+            " Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.629\n",
+            " Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.681\n",
+            " Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.524\n",
+            " Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.735\n",
+            " Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.827\n",
+            "Results saved to \u001b[1mruns/val/exp\u001b[0m\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "rc_KbFk0juX2"
+      },
+      "source": [
+        "## COCO test-dev2017\n",
+        "Download [COCO test2017](https://github.com/ultralytics/yolov5/blob/74b34872fdf41941cddcf243951cdb090fbac17b/data/coco.yaml#L15) dataset (7GB - 40,000 images), to test model accuracy on test-dev set (**20,000 images, no labels**). Results are saved to a `*.json` file which should be **zipped** and submitted to the evaluation server at https://competitions.codalab.org/competitions/20794."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "V0AJnSeCIHyJ"
+      },
+      "source": [
+        "# Download COCO test-dev2017\n",
+        "torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017labels.zip', 'tmp.zip')\n",
+        "!unzip -q tmp.zip -d ../ && rm tmp.zip # unzip labels\n",
+        "!f=\"test2017.zip\" && curl http://images.cocodataset.org/zips/$f -o $f && unzip -q $f && rm $f  # 7GB,  41k images\n",
+        "%mv ./test2017 ../coco/images  # move to /coco"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "29GJXAP_lPrt"
+      },
+      "source": [
+        "# Run YOLOv5s on COCO test-dev2017 using --task test\n",
+        "!python val.py --weights yolov5s.pt --data coco.yaml --task test"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "VUOiNLtMP5aG"
+      },
+      "source": [
+        "# 3. Train\n",
+        "\n",
+        "Download [COCO128](https://www.kaggle.com/ultralytics/coco128), a small 128-image tutorial dataset, start tensorboard and train YOLOv5s from a pretrained checkpoint for 3 epochs (note actual training is typically much longer, around **300-1000 epochs**, depending on your dataset)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "Knxi2ncxWffW"
+      },
+      "source": [
+        "# Download COCO128\n",
+        "torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip', 'tmp.zip')\n",
+        "!unzip -q tmp.zip -d ../datasets && rm tmp.zip"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "_pOkGLv1dMqh"
+      },
+      "source": [
+        "Train a YOLOv5s model on [COCO128](https://www.kaggle.com/ultralytics/coco128) with `--data coco128.yaml`, starting from pretrained `--weights yolov5s.pt`, or from randomly initialized `--weights '' --cfg yolov5s.yaml`. Models are downloaded automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases), and **COCO, COCO128, and VOC datasets are downloaded automatically** on first use.\n",
+        "\n",
+        "All training results are saved to `runs/train/` with incrementing run directories, i.e. `runs/train/exp2`, `runs/train/exp3` etc.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "bOy5KI2ncnWd"
+      },
+      "source": [
+        "# Tensorboard  (optional)\n",
+        "%load_ext tensorboard\n",
+        "%tensorboard --logdir runs/train"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "2fLAV42oNb7M"
+      },
+      "source": [
+        "# Weights & Biases  (optional)\n",
+        "%pip install -q wandb\n",
+        "import wandb\n",
+        "wandb.login()"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "1NcFxRcFdJ_O",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "00ea4b14-a75c-44a2-a913-03b431b69de5"
+      },
+      "source": [
+        "# Train YOLOv5s on COCO128 for 3 epochs\n",
+        "!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov5s.pt, cfg=, data=coco128.yaml, hyp=data/hyps/hyp.scratch.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, adam=False, sync_bn=False, workers=8, project=runs/train, entity=None, name=exp, exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, upload_dataset=False, bbox_interval=-1, save_period=-1, artifact_alias=latest, local_rank=-1, freeze=0\n",
+            "\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 ✅\n",
+            "YOLOv5 🚀 v5.0-367-g01cdb76 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",
+            "\n",
+            "\u001b[34m\u001b[1mhyperparameters: \u001b[0mlr0=0.01, lrf=0.2, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0\n",
+            "\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)\n",
+            "\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n",
+            "2021-08-15 14:40:43.449642: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.11.0\n",
+            "\n",
+            "                 from  n    params  module                                  arguments                     \n",
+            "  0                -1  1      3520  models.common.Focus                     [3, 32, 3]                    \n",
+            "  1                -1  1     18560  models.common.Conv                      [32, 64, 3, 2]                \n",
+            "  2                -1  1     18816  models.common.C3                        [64, 64, 1]                   \n",
+            "  3                -1  1     73984  models.common.Conv                      [64, 128, 3, 2]               \n",
+            "  4                -1  3    156928  models.common.C3                        [128, 128, 3]                 \n",
+            "  5                -1  1    295424  models.common.Conv                      [128, 256, 3, 2]              \n",
+            "  6                -1  3    625152  models.common.C3                        [256, 256, 3]                 \n",
+            "  7                -1  1   1180672  models.common.Conv                      [256, 512, 3, 2]              \n",
+            "  8                -1  1    656896  models.common.SPP                       [512, 512, [5, 9, 13]]        \n",
+            "  9                -1  1   1182720  models.common.C3                        [512, 512, 1, False]          \n",
+            " 10                -1  1    131584  models.common.Conv                      [512, 256, 1, 1]              \n",
+            " 11                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          \n",
+            " 12           [-1, 6]  1         0  models.common.Concat                    [1]                           \n",
+            " 13                -1  1    361984  models.common.C3                        [512, 256, 1, False]          \n",
+            " 14                -1  1     33024  models.common.Conv                      [256, 128, 1, 1]              \n",
+            " 15                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          \n",
+            " 16           [-1, 4]  1         0  models.common.Concat                    [1]                           \n",
+            " 17                -1  1     90880  models.common.C3                        [256, 128, 1, False]          \n",
+            " 18                -1  1    147712  models.common.Conv                      [128, 128, 3, 2]              \n",
+            " 19          [-1, 14]  1         0  models.common.Concat                    [1]                           \n",
+            " 20                -1  1    296448  models.common.C3                        [256, 256, 1, False]          \n",
+            " 21                -1  1    590336  models.common.Conv                      [256, 256, 3, 2]              \n",
+            " 22          [-1, 10]  1         0  models.common.Concat                    [1]                           \n",
+            " 23                -1  1   1182720  models.common.C3                        [512, 512, 1, False]          \n",
+            " 24      [17, 20, 23]  1    229245  models.yolo.Detect                      [80, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]\n",
+            "Model Summary: 283 layers, 7276605 parameters, 7276605 gradients, 17.1 GFLOPs\n",
+            "\n",
+            "Transferred 362/362 items from yolov5s.pt\n",
+            "Scaled weight_decay = 0.0005\n",
+            "\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 59 weight, 62 weight (no decay), 62 bias\n",
+            "\u001b[34m\u001b[1malbumentations: \u001b[0mversion 1.0.3 required by YOLOv5, but version 0.1.12 is currently installed\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mScanning '../datasets/coco128/labels/train2017' images and labels...128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<00:00, 2440.28it/s]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: ../datasets/coco128/labels/train2017.cache\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 302.61it/s]\n",
+            "\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<?, ?it/s]\n",
+            "\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 142.55it/s]\n",
+            "[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)\n",
+            "[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)\n",
+            "Plotting labels... \n",
+            "\n",
+            "\u001b[34m\u001b[1mautoanchor: \u001b[0mAnalyzing anchors... anchors/target = 4.27, Best Possible Recall (BPR) = 0.9935\n",
+            "Image sizes 640 train, 640 val\n",
+            "Using 2 dataloader workers\n",
+            "Logging results to runs/train/exp\n",
+            "Starting training for 3 epochs...\n",
+            "\n",
+            "     Epoch   gpu_mem       box       obj       cls    labels  img_size\n",
+            "       0/2     3.64G   0.04492    0.0674   0.02213       298       640: 100% 8/8 [00:03<00:00,  2.05it/s]\n",
+            "               Class     Images     Labels          P          R     [email protected] [email protected]:.95: 100% 4/4 [00:00<00:00,  4.70it/s]\n",
+            "                 all        128        929      0.686      0.565      0.642      0.421\n",
+            "\n",
+            "     Epoch   gpu_mem       box       obj       cls    labels  img_size\n",
+            "       1/2     5.04G   0.04403    0.0611   0.01986       232       640: 100% 8/8 [00:01<00:00,  5.59it/s]\n",
+            "               Class     Images     Labels          P          R     [email protected] [email protected]:.95: 100% 4/4 [00:00<00:00,  4.46it/s]\n",
+            "                 all        128        929      0.694      0.563      0.654      0.425\n",
+            "\n",
+            "     Epoch   gpu_mem       box       obj       cls    labels  img_size\n",
+            "       2/2     5.04G   0.04616   0.07056   0.02071       214       640: 100% 8/8 [00:01<00:00,  5.94it/s]\n",
+            "               Class     Images     Labels          P          R     [email protected] [email protected]:.95: 100% 4/4 [00:02<00:00,  1.52it/s]\n",
+            "                 all        128        929      0.711      0.562       0.66      0.431\n",
+            "\n",
+            "3 epochs completed in 0.005 hours.\n",
+            "Optimizer stripped from runs/train/exp/weights/last.pt, 14.8MB\n",
+            "Optimizer stripped from runs/train/exp/weights/best.pt, 14.8MB\n",
+            "Results saved to \u001b[1mruns/train/exp\u001b[0m\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "15glLzbQx5u0"
+      },
+      "source": [
+        "# 4. Visualize"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "DLI1JmHU7B0l"
+      },
+      "source": [
+        "## Weights & Biases Logging 🌟 NEW\n",
+        "\n",
+        "[Weights & Biases](https://wandb.ai/site?utm_campaign=repo_yolo_notebook) (W&B) is now integrated with YOLOv5 for real-time visualization and cloud logging of training runs. This allows for better run comparison and introspection, as well improved visibility and collaboration for teams. To enable W&B `pip install wandb`, and then train normally (you will be guided through setup on first use). \n",
+        "\n",
+        "During training you will see live updates at [https://wandb.ai/home](https://wandb.ai/home?utm_campaign=repo_yolo_notebook), and you can create and share detailed [Reports](https://wandb.ai/glenn-jocher/yolov5_tutorial/reports/YOLOv5-COCO128-Tutorial-Results--VmlldzozMDI5OTY) of your results. For more information see the [YOLOv5 Weights & Biases Tutorial](https://github.com/ultralytics/yolov5/issues/1289). \n",
+        "\n",
+        "<img align=\"left\" src=\"https://user-images.githubusercontent.com/26833433/125274843-a27bc600-e30e-11eb-9a44-62af0b7a50a2.png\" width=\"800\">"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "-WPvRbS5Swl6"
+      },
+      "source": [
+        "## Local Logging\n",
+        "\n",
+        "All results are logged by default to `runs/train`, with a new experiment directory created for each new training as `runs/train/exp2`, `runs/train/exp3`, etc. View train and val jpgs to see mosaics, labels, predictions and augmentation effects. Note an Ultralytics **Mosaic Dataloader** is used for training (shown below), which combines 4 images into 1 mosaic during training.\n",
+        "\n",
+        "> <img src=\"https://user-images.githubusercontent.com/26833433/131255960-b536647f-7c61-4f60-bbc5-cb2544d71b2a.jpg\" width=\"700\">  \n",
+        "`train_batch0.jpg` shows train batch 0 mosaics and labels\n",
+        "\n",
+        "> <img src=\"https://user-images.githubusercontent.com/26833433/131256748-603cafc7-55d1-4e58-ab26-83657761aed9.jpg\" width=\"700\">  \n",
+        "`test_batch0_labels.jpg` shows val batch 0 labels\n",
+        "\n",
+        "> <img src=\"https://user-images.githubusercontent.com/26833433/131256752-3f25d7a5-7b0f-4bb3-ab78-46343c3800fe.jpg\" width=\"700\">  \n",
+        "`test_batch0_pred.jpg` shows val batch 0 _predictions_\n",
+        "\n",
+        "Training results are automatically logged to [Tensorboard](https://www.tensorflow.org/tensorboard) and [CSV](https://github.com/ultralytics/yolov5/pull/4148) as `results.csv`, which is plotted as `results.png` (below) after training completes. You can also plot any `results.csv` file manually:\n",
+        "\n",
+        "```python\n",
+        "from utils.plots import plot_results \n",
+        "plot_results('path/to/results.csv')  # plot 'results.csv' as 'results.png'\n",
+        "```\n",
+        "\n",
+        "<img align=\"left\" width=\"800\" alt=\"COCO128 Training Results\" src=\"https://user-images.githubusercontent.com/26833433/126906780-8c5e2990-6116-4de6-b78a-367244a33ccf.png\">"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Zelyeqbyt3GD"
+      },
+      "source": [
+        "# Environments\n",
+        "\n",
+        "YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled):\n",
+        "\n",
+        "- **Google Colab and Kaggle** notebooks with free GPU: <a href=\"https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"></a> <a href=\"https://www.kaggle.com/ultralytics/yolov5\"><img src=\"https://kaggle.com/static/images/open-in-kaggle.svg\" alt=\"Open In Kaggle\"></a>\n",
+        "- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart)\n",
+        "- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart)\n",
+        "- **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) <a href=\"https://hub.docker.com/r/ultralytics/yolov5\"><img src=\"https://img.shields.io/docker/pulls/ultralytics/yolov5?logo=docker\" alt=\"Docker Pulls\"></a>\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6Qu7Iesl0p54"
+      },
+      "source": [
+        "# Status\n",
+        "\n",
+        "![CI CPU testing](https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg)\n",
+        "\n",
+        "If this badge is green, all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training ([train.py](https://github.com/ultralytics/yolov5/blob/master/train.py)), testing ([val.py](https://github.com/ultralytics/yolov5/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov5/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov5/blob/master/export.py)) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "IEijrePND_2I"
+      },
+      "source": [
+        "# Appendix\n",
+        "\n",
+        "Optional extras below. Unit tests validate repo functionality and should be run on any PRs submitted.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "mcKoSIK2WSzj"
+      },
+      "source": [
+        "# Reproduce\n",
+        "for x in 'yolov5s', 'yolov5m', 'yolov5l', 'yolov5x':\n",
+        "  !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.25 --iou 0.45  # speed\n",
+        "  !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.001 --iou 0.65  # mAP"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "GMusP4OAxFu6"
+      },
+      "source": [
+        "# PyTorch Hub\n",
+        "import torch\n",
+        "\n",
+        "# Model\n",
+        "model = torch.hub.load('ultralytics/yolov5', 'yolov5s')\n",
+        "\n",
+        "# Images\n",
+        "dir = 'https://ultralytics.com/images/'\n",
+        "imgs = [dir + f for f in ('zidane.jpg', 'bus.jpg')]  # batch of images\n",
+        "\n",
+        "# Inference\n",
+        "results = model(imgs)\n",
+        "results.print()  # or .show(), .save()"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "FGH0ZjkGjejy"
+      },
+      "source": [
+        "# Unit tests\n",
+        "%%shell\n",
+        "export PYTHONPATH=\"$PWD\"  # to run *.py. files in subdirectories\n",
+        "\n",
+        "rm -rf runs  # remove runs/\n",
+        "for m in yolov5s; do  # models\n",
+        "  python train.py --weights $m.pt --epochs 3 --img 320 --device 0  # train pretrained\n",
+        "  python train.py --weights '' --cfg $m.yaml --epochs 3 --img 320 --device 0  # train scratch\n",
+        "  for d in 0 cpu; do  # devices\n",
+        "    python detect.py --weights $m.pt --device $d  # detect official\n",
+        "    python detect.py --weights runs/train/exp/weights/best.pt --device $d  # detect custom\n",
+        "    python val.py --weights $m.pt --device $d # val official\n",
+        "    python val.py --weights runs/train/exp/weights/best.pt --device $d # val custom\n",
+        "  done\n",
+        "  python hubconf.py  # hub\n",
+        "  python models/yolo.py --cfg $m.yaml  # inspect\n",
+        "  python export.py --weights $m.pt --img 640 --batch 1  # export\n",
+        "done"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "gogI-kwi3Tye"
+      },
+      "source": [
+        "# Profile\n",
+        "from utils.torch_utils import profile\n",
+        "\n",
+        "m1 = lambda x: x * torch.sigmoid(x)\n",
+        "m2 = torch.nn.SiLU()\n",
+        "results = profile(input=torch.randn(16, 3, 640, 640), ops=[m1, m2], n=100)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "RVRSOhEvUdb5"
+      },
+      "source": [
+        "# Evolve\n",
+        "!python train.py --img 640 --batch 64 --epochs 100 --data coco128.yaml --weights yolov5s.pt --cache --noautoanchor --evolve\n",
+        "!d=runs/train/evolve && cp evolve.* $d && zip -r evolve.zip $d && gsutil mv evolve.zip gs://bucket  # upload results (optional)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "BSgFCAcMbk1R"
+      },
+      "source": [
+        "# VOC\n",
+        "for b, m in zip([64, 48, 32, 16], ['yolov5s', 'yolov5m', 'yolov5l', 'yolov5x']):  # zip(batch_size, model)\n",
+        "  !python train.py --batch {b} --weights {m}.pt --data VOC.yaml --epochs 50 --cache --img 512 --nosave --hyp hyp.finetune.yaml --project VOC --name {m}"
+      ],
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

utils.py

@@ -0,0 +1,61 @@
+import json
+import os
+
+# from sklearn.externals import joblib
+import joblib
+import numpy as np
+import pandas as pd
+
+# from .variables import old_ocr_req_cols
+# from .skew_correction import  PageSkewWraper
+
+const_HW = 1.294117647
+const_W = 600
+
+
+def bucket_sort(df, colmn, ymax_col="ymax", ymin_col="ymin"):
+    df["line_number"] = 0
+    colmn.append("line_number")
+    array_value = df[colmn].values
+    start_index = Line_counter = counter = 0
+    ymax, ymin, line_no = (
+        colmn.index(ymax_col),
+        colmn.index(ymin_col),
+        colmn.index("line_number"),
+    )
+    while counter < len(array_value):
+        current_ymax = array_value[start_index][ymax]
+        for next_index in range(start_index, len(array_value)):
+            counter += 1
+
+            next_ymin = array_value[next_index][ymin]
+            next_ymax = array_value[next_index][ymax]
+            if current_ymax > next_ymin:
+
+                array_value[next_index][line_no] = Line_counter + 1
+            #                 if current_ymax < next_ymax:
+
+            #                     current_ymax = next_ymax
+            else:
+                counter -= 1
+                break
+        # print(counter, len(array_value), start_index)
+        start_index = counter
+        Line_counter += 1
+    return pd.DataFrame(array_value, columns=colmn)
+
+
+def do_sorting(df):
+    df.sort_values(["ymin", "xmin"], ascending=True, inplace=True)
+    df["idx"] = df.index
+    if "line_number" in df.columns:
+        print("line number removed")
+        df.drop("line_number", axis=1, inplace=True)
+    req_colns = ["xmin", "ymin", "xmax", "ymax", "idx"]
+    temp_df = df.copy()
+    temp = bucket_sort(temp_df.copy(), req_colns)
+    df = df.merge(temp[["idx", "line_number"]], on="idx")
+    df.sort_values(["line_number", "xmin"], ascending=True, inplace=True)
+    df = df.reset_index(drop=True)
+    df = df.reset_index(drop=True)
+    return df

val.py

@@ -0,0 +1,593 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Validate a trained YOLOv5 model accuracy on a custom dataset
+
+Usage:
+    $ python path/to/val.py --data coco128.yaml --weights yolov5s.pt --img 640
+"""
+
+import argparse
+import json
+import os
+import sys
+from pathlib import Path
+from threading import Thread
+
+import numpy as np
+import torch
+from tqdm import tqdm
+
+FILE = Path(__file__).absolute()
+sys.path.append(FILE.parents[0].as_posix())  # add yolov5/ to path
+
+from models.experimental import attempt_load
+from utils.callbacks import Callbacks
+from utils.datasets import create_dataloader
+from utils.general import (
+    box_iou,
+    check_dataset,
+    check_img_size,
+    check_requirements,
+    check_suffix,
+    check_yaml,
+    coco80_to_coco91_class,
+    colorstr,
+    increment_path,
+    non_max_suppression,
+    scale_coords,
+    set_logging,
+    xywh2xyxy,
+    xyxy2xywh,
+)
+from utils.metrics import ConfusionMatrix, ap_per_class
+from utils.plots import output_to_target, plot_images, plot_study_txt
+from utils.torch_utils import select_device, time_sync
+
+
+def save_one_txt(predn, save_conf, shape, file):
+    # Save one txt result
+    gn = torch.tensor(shape)[[1, 0, 1, 0]]  # normalization gain whwh
+    for *xyxy, conf, cls in predn.tolist():
+        xywh = (
+            (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()
+        )  # normalized xywh
+        line = (
+            (cls, *xywh, conf) if save_conf else (cls, *xywh)
+        )  # label format
+        with open(file, "a") as f:
+            f.write(("%g " * len(line)).rstrip() % line + "\n")
+
+
+def save_one_json(predn, jdict, path, class_map):
+    # Save one JSON result {"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}
+    image_id = int(path.stem) if path.stem.isnumeric() else path.stem
+    box = xyxy2xywh(predn[:, :4])  # xywh
+    box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
+    for p, b in zip(predn.tolist(), box.tolist()):
+        jdict.append(
+            {
+                "image_id": image_id,
+                "category_id": class_map[int(p[5])],
+                "bbox": [round(x, 3) for x in b],
+                "score": round(p[4], 5),
+            }
+        )
+
+
+def process_batch(detections, labels, iouv):
+    """
+    Return correct predictions matrix. Both sets of boxes are in (x1, y1, x2, y2) format.
+    Arguments:
+        detections (Array[N, 6]), x1, y1, x2, y2, conf, class
+        labels (Array[M, 5]), class, x1, y1, x2, y2
+    Returns:
+        correct (Array[N, 10]), for 10 IoU levels
+    """
+    correct = torch.zeros(
+        detections.shape[0],
+        iouv.shape[0],
+        dtype=torch.bool,
+        device=iouv.device,
+    )
+    iou = box_iou(labels[:, 1:], detections[:, :4])
+    x = torch.where(
+        (iou >= iouv[0]) & (labels[:, 0:1] == detections[:, 5])
+    )  # IoU above threshold and classes match
+    if x[0].shape[0]:
+        matches = (
+            torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1)
+            .cpu()
+            .numpy()
+        )  # [label, detection, iou]
+        if x[0].shape[0] > 1:
+            matches = matches[matches[:, 2].argsort()[::-1]]
+            matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
+            # matches = matches[matches[:, 2].argsort()[::-1]]
+            matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
+        matches = torch.Tensor(matches).to(iouv.device)
+        correct[matches[:, 1].long()] = matches[:, 2:3] >= iouv
+    return correct
+
+
+@torch.no_grad()
+def run(
+    data,
+    weights=None,  # model.pt path(s)
+    batch_size=32,  # batch size
+    imgsz=640,  # inference size (pixels)
+    conf_thres=0.001,  # confidence threshold
+    iou_thres=0.6,  # NMS IoU threshold
+    task="val",  # train, val, test, speed or study
+    device="",  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+    single_cls=False,  # treat as single-class dataset
+    augment=False,  # augmented inference
+    verbose=False,  # verbose output
+    save_txt=False,  # save results to *.txt
+    save_hybrid=False,  # save label+prediction hybrid results to *.txt
+    save_conf=False,  # save confidences in --save-txt labels
+    save_json=False,  # save a COCO-JSON results file
+    project="runs/val",  # save to project/name
+    name="exp",  # save to project/name
+    exist_ok=False,  # existing project/name ok, do not increment
+    half=True,  # use FP16 half-precision inference
+    model=None,
+    dataloader=None,
+    save_dir=Path(""),
+    plots=True,
+    callbacks=Callbacks(),
+    compute_loss=None,
+):
+    # Initialize/load model and set device
+    training = model is not None
+    if training:  # called by train.py
+        device = next(model.parameters()).device  # get model device
+
+    else:  # called directly
+        device = select_device(device, batch_size=batch_size)
+
+        # Directories
+        save_dir = increment_path(
+            Path(project) / name, exist_ok=exist_ok
+        )  # increment run
+        (save_dir / "labels" if save_txt else save_dir).mkdir(
+            parents=True, exist_ok=True
+        )  # make dir
+
+        # Load model
+        check_suffix(weights, ".pt")
+        model = attempt_load(weights, map_location=device)  # load FP32 model
+        gs = max(int(model.stride.max()), 32)  # grid size (max stride)
+        imgsz = check_img_size(imgsz, s=gs)  # check image size
+
+        # Multi-GPU disabled, incompatible with .half() https://github.com/ultralytics/yolov5/issues/99
+        # if device.type != 'cpu' and torch.cuda.device_count() > 1:
+        #     model = nn.DataParallel(model)
+
+        # Data
+        data = check_dataset(data)  # check
+
+    # Half
+    half &= device.type != "cpu"  # half precision only supported on CUDA
+    if half:
+        model.half()
+
+    # Configure
+    model.eval()
+    is_coco = isinstance(data.get("val"), str) and data["val"].endswith(
+        "coco/val2017.txt"
+    )  # COCO dataset
+    nc = 1 if single_cls else int(data["nc"])  # number of classes
+    iouv = torch.linspace(0.5, 0.95, 10).to(
+        device
+    )  # iou vector for [email protected]:0.95
+    niou = iouv.numel()
+
+    # Dataloader
+    if not training:
+        if device.type != "cpu":
+            model(
+                torch.zeros(1, 3, imgsz, imgsz)
+                .to(device)
+                .type_as(next(model.parameters()))
+            )  # run once
+        task = (
+            task if task in ("train", "val", "test") else "val"
+        )  # path to train/val/test images
+        dataloader = create_dataloader(
+            data[task],
+            imgsz,
+            batch_size,
+            gs,
+            single_cls,
+            pad=0.5,
+            rect=True,
+            prefix=colorstr(f"{task}: "),
+        )[0]
+
+    seen = 0
+    confusion_matrix = ConfusionMatrix(nc=nc)
+    names = {
+        k: v
+        for k, v in enumerate(
+            model.names if hasattr(model, "names") else model.module.names
+        )
+    }
+    class_map = coco80_to_coco91_class() if is_coco else list(range(1000))
+    s = ("%20s" + "%11s" * 6) % (
+        "Class",
+        "Images",
+        "Labels",
+        "P",
+        "R",
+        "[email protected]",
+        "[email protected]:.95",
+    )
+    dt, p, r, f1, mp, mr, map50, map = (
+        [0.0, 0.0, 0.0],
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+    )
+    loss = torch.zeros(3, device=device)
+    jdict, stats, ap, ap_class = [], [], [], []
+    for batch_i, (img, targets, paths, shapes) in enumerate(
+        tqdm(dataloader, desc=s)
+    ):
+        t1 = time_sync()
+        img = img.to(device, non_blocking=True)
+        img = img.half() if half else img.float()  # uint8 to fp16/32
+        img /= 255.0  # 0 - 255 to 0.0 - 1.0
+        targets = targets.to(device)
+        nb, _, height, width = img.shape  # batch size, channels, height, width
+        t2 = time_sync()
+        dt[0] += t2 - t1
+
+        # Run model
+        out, train_out = model(
+            img, augment=augment
+        )  # inference and training outputs
+        dt[1] += time_sync() - t2
+
+        # Compute loss
+        if compute_loss:
+            loss += compute_loss([x.float() for x in train_out], targets)[
+                1
+            ]  # box, obj, cls
+
+        # Run NMS
+        targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(
+            device
+        )  # to pixels
+        lb = (
+            [targets[targets[:, 0] == i, 1:] for i in range(nb)]
+            if save_hybrid
+            else []
+        )  # for autolabelling
+        t3 = time_sync()
+        out = non_max_suppression(
+            out,
+            conf_thres,
+            iou_thres,
+            labels=lb,
+            multi_label=True,
+            agnostic=single_cls,
+        )
+        dt[2] += time_sync() - t3
+
+        # Statistics per image
+        for si, pred in enumerate(out):
+            labels = targets[targets[:, 0] == si, 1:]
+            nl = len(labels)
+            tcls = labels[:, 0].tolist() if nl else []  # target class
+            path, shape = Path(paths[si]), shapes[si][0]
+            seen += 1
+
+            if len(pred) == 0:
+                if nl:
+                    stats.append(
+                        (
+                            torch.zeros(0, niou, dtype=torch.bool),
+                            torch.Tensor(),
+                            torch.Tensor(),
+                            tcls,
+                        )
+                    )
+                continue
+
+            # Predictions
+            if single_cls:
+                pred[:, 5] = 0
+            predn = pred.clone()
+            scale_coords(
+                img[si].shape[1:], predn[:, :4], shape, shapes[si][1]
+            )  # native-space pred
+
+            # Evaluate
+            if nl:
+                tbox = xywh2xyxy(labels[:, 1:5])  # target boxes
+                scale_coords(
+                    img[si].shape[1:], tbox, shape, shapes[si][1]
+                )  # native-space labels
+                labelsn = torch.cat(
+                    (labels[:, 0:1], tbox), 1
+                )  # native-space labels
+                correct = process_batch(predn, labelsn, iouv)
+                if plots:
+                    confusion_matrix.process_batch(predn, labelsn)
+            else:
+                correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool)
+            stats.append(
+                (correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls)
+            )  # (correct, conf, pcls, tcls)
+
+            # Save/log
+            if save_txt:
+                save_one_txt(
+                    predn,
+                    save_conf,
+                    shape,
+                    file=save_dir / "labels" / (path.stem + ".txt"),
+                )
+            if save_json:
+                save_one_json(
+                    predn, jdict, path, class_map
+                )  # append to COCO-JSON dictionary
+            callbacks.run(
+                "on_val_image_end", pred, predn, path, names, img[si]
+            )
+
+        # Plot images
+        if plots and batch_i < 3:
+            f = save_dir / f"val_batch{batch_i}_labels.jpg"  # labels
+            Thread(
+                target=plot_images,
+                args=(img, targets, paths, f, names),
+                daemon=True,
+            ).start()
+            f = save_dir / f"val_batch{batch_i}_pred.jpg"  # predictions
+            Thread(
+                target=plot_images,
+                args=(img, output_to_target(out), paths, f, names),
+                daemon=True,
+            ).start()
+
+    # Compute statistics
+    stats = [np.concatenate(x, 0) for x in zip(*stats)]  # to numpy
+    if len(stats) and stats[0].any():
+        p, r, ap, f1, ap_class = ap_per_class(
+            *stats, plot=plots, save_dir=save_dir, names=names
+        )
+        ap50, ap = ap[:, 0], ap.mean(1)  # [email protected], [email protected]:0.95
+        mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean()
+        nt = np.bincount(
+            stats[3].astype(np.int64), minlength=nc
+        )  # number of targets per class
+    else:
+        nt = torch.zeros(1)
+
+    # Print results
+    pf = "%20s" + "%11i" * 2 + "%11.3g" * 4  # print format
+    print(pf % ("all", seen, nt.sum(), mp, mr, map50, map))
+
+    # Print results per class
+    if (verbose or (nc < 50 and not training)) and nc > 1 and len(stats):
+        for i, c in enumerate(ap_class):
+            print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i]))
+
+    # Print speeds
+    t = tuple(x / seen * 1e3 for x in dt)  # speeds per image
+    if not training:
+        shape = (batch_size, 3, imgsz, imgsz)
+        print(
+            f"Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {shape}"
+            % t
+        )
+
+    # Plots
+    if plots:
+        confusion_matrix.plot(save_dir=save_dir, names=list(names.values()))
+        callbacks.run("on_val_end")
+
+    # Save JSON
+    if save_json and len(jdict):
+        w = (
+            Path(weights[0] if isinstance(weights, list) else weights).stem
+            if weights is not None
+            else ""
+        )  # weights
+        anno_json = str(
+            Path(data.get("path", "../coco"))
+            / "annotations/instances_val2017.json"
+        )  # annotations json
+        pred_json = str(save_dir / f"{w}_predictions.json")  # predictions json
+        print(f"\nEvaluating pycocotools mAP... saving {pred_json}...")
+        with open(pred_json, "w") as f:
+            json.dump(jdict, f)
+
+        try:  # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
+            check_requirements(["pycocotools"])
+            from pycocotools.coco import COCO
+            from pycocotools.cocoeval import COCOeval
+
+            anno = COCO(anno_json)  # init annotations api
+            pred = anno.loadRes(pred_json)  # init predictions api
+            eval = COCOeval(anno, pred, "bbox")
+            if is_coco:
+                eval.params.imgIds = [
+                    int(Path(x).stem) for x in dataloader.dataset.img_files
+                ]  # image IDs to evaluate
+            eval.evaluate()
+            eval.accumulate()
+            eval.summarize()
+            map, map50 = eval.stats[
+                :2
+            ]  # update results ([email protected]:0.95, [email protected])
+        except Exception as e:
+            print(f"pycocotools unable to run: {e}")
+
+    # Return results
+    model.float()  # for training
+    if not training:
+        s = (
+            f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}"
+            if save_txt
+            else ""
+        )
+        print(f"Results saved to {colorstr('bold', save_dir)}{s}")
+    maps = np.zeros(nc) + map
+    for i, c in enumerate(ap_class):
+        maps[c] = ap[i]
+    return (
+        (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()),
+        maps,
+        t,
+    )
+
+
+def parse_opt():
+    parser = argparse.ArgumentParser(prog="val.py")
+    parser.add_argument(
+        "--data",
+        type=str,
+        default="data/coco128.yaml",
+        help="dataset.yaml path",
+    )
+    parser.add_argument(
+        "--weights",
+        nargs="+",
+        type=str,
+        default="yolov5s.pt",
+        help="model.pt path(s)",
+    )
+    parser.add_argument(
+        "--batch-size", type=int, default=32, help="batch size"
+    )
+    parser.add_argument(
+        "--imgsz",
+        "--img",
+        "--img-size",
+        type=int,
+        default=640,
+        help="inference size (pixels)",
+    )
+    parser.add_argument(
+        "--conf-thres", type=float, default=0.001, help="confidence threshold"
+    )
+    parser.add_argument(
+        "--iou-thres", type=float, default=0.6, help="NMS IoU threshold"
+    )
+    parser.add_argument(
+        "--task", default="val", help="train, val, test, speed or study"
+    )
+    parser.add_argument(
+        "--device", default="", help="cuda device, i.e. 0 or 0,1,2,3 or cpu"
+    )
+    parser.add_argument(
+        "--single-cls",
+        action="store_true",
+        help="treat as single-class dataset",
+    )
+    parser.add_argument(
+        "--augment", action="store_true", help="augmented inference"
+    )
+    parser.add_argument(
+        "--verbose", action="store_true", help="report mAP by class"
+    )
+    parser.add_argument(
+        "--save-txt", action="store_true", help="save results to *.txt"
+    )
+    parser.add_argument(
+        "--save-hybrid",
+        action="store_true",
+        help="save label+prediction hybrid results to *.txt",
+    )
+    parser.add_argument(
+        "--save-conf",
+        action="store_true",
+        help="save confidences in --save-txt labels",
+    )
+    parser.add_argument(
+        "--save-json",
+        action="store_true",
+        help="save a COCO-JSON results file",
+    )
+    parser.add_argument(
+        "--project", default="runs/val", help="save to project/name"
+    )
+    parser.add_argument("--name", default="exp", help="save to project/name")
+    parser.add_argument(
+        "--exist-ok",
+        action="store_true",
+        help="existing project/name ok, do not increment",
+    )
+    parser.add_argument(
+        "--half", action="store_true", help="use FP16 half-precision inference"
+    )
+    opt = parser.parse_args()
+    opt.save_json |= opt.data.endswith("coco.yaml")
+    opt.save_txt |= opt.save_hybrid
+    opt.data = check_yaml(opt.data)  # check YAML
+    return opt
+
+
+def main(opt):
+    set_logging()
+    print(
+        colorstr("val: ") + ", ".join(f"{k}={v}" for k, v in vars(opt).items())
+    )
+    check_requirements(
+        requirements=FILE.parent / "requirements.txt",
+        exclude=("tensorboard", "thop"),
+    )
+
+    if opt.task in ("train", "val", "test"):  # run normally
+        run(**vars(opt))
+
+    elif opt.task == "speed":  # speed benchmarks
+        for w in (
+            opt.weights if isinstance(opt.weights, list) else [opt.weights]
+        ):
+            run(
+                opt.data,
+                weights=w,
+                batch_size=opt.batch_size,
+                imgsz=opt.imgsz,
+                conf_thres=0.25,
+                iou_thres=0.45,
+                save_json=False,
+                plots=False,
+            )
+
+    elif opt.task == "study":  # run over a range of settings and save/plot
+        # python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5s.pt yolov5m.pt yolov5l.pt yolov5x.pt
+        x = list(range(256, 1536 + 128, 128))  # x axis (image sizes)
+        for w in (
+            opt.weights if isinstance(opt.weights, list) else [opt.weights]
+        ):
+            f = f"study_{Path(opt.data).stem}_{Path(w).stem}.txt"  # filename to save to
+            y = []  # y axis
+            for i in x:  # img-size
+                print(f"\nRunning {f} point {i}...")
+                r, _, t = run(
+                    opt.data,
+                    weights=w,
+                    batch_size=opt.batch_size,
+                    imgsz=i,
+                    conf_thres=opt.conf_thres,
+                    iou_thres=opt.iou_thres,
+                    save_json=opt.save_json,
+                    plots=False,
+                )
+                y.append(r + t)  # results and times
+            np.savetxt(f, y, fmt="%10.4g")  # save
+        os.system("zip -r study.zip study_*.txt")
+        plot_study_txt(x=x)  # plot
+
+
+if __name__ == "__main__":
+    opt = parse_opt()
+    main(opt)

yolo_inference_util.py

@@ -0,0 +1,369 @@
+import argparse
+import sys
+from pathlib import Path
+
+import cv2
+import numpy as np
+import torch
+import torch.backends.cudnn as cudnn
+
+from models.experimental import attempt_load
+from utils.datasets import LoadImages, LoadStreams
+from utils.general import (
+    apply_classifier,
+    check_img_size,
+    check_imshow,
+    check_requirements,
+    check_suffix,
+    colorstr,
+    increment_path,
+    is_ascii,
+    non_max_suppression,
+    save_one_box,
+    scale_coords,
+    set_logging,
+    strip_optimizer,
+    xyxy2xywh,
+)
+from utils.plots import Annotator, colors
+from utils.torch_utils import load_classifier, select_device, time_sync
+
+# FILE = Path(__file__).resolve()
+# ROOT = FILE.parents[0]  # YOLOv5 root directory
+# if str(ROOT) not in sys.path:
+#     sys.path.append(str(ROOT))  # add ROOT to PATH
+
+
+
+@torch.no_grad()
+def run_yolo_v5(
+    weights="yolov5s.pt",  # model.pt path(s)
+    source="data/images",  # file/dir/URL/glob, 0 for webcam
+    imgsz=640,  # inference size (pixels)
+    conf_thres=0.25,  # confidence threshold
+    iou_thres=0.45,  # NMS IOU threshold
+    max_det=1000,  # maximum detections per image
+    device="",  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+    view_img=False,  # show results
+    save_txt=False,  # save results to *.txt
+    save_conf=False,  # save confidences in --save-txt labels
+    save_crop=False,  # save cropped prediction boxes
+    nosave=False,  # do not save images/videos
+    classes=None,  # filter by class: --class 0, or --class 0 2 3
+    agnostic_nms=False,  # class-agnostic NMS
+    augment=False,  # augmented inference
+    visualize=False,  # visualize features
+    update=False,  # update all models
+    project="runs/detect",  # save results to project/name
+    name="exp",  # save results to project/name
+    exist_ok=False,  # existing project/name ok, do not increment
+    line_thickness=3,  # bounding box thickness (pixels)
+    hide_labels=False,  # hide labels
+    hide_conf=False,  # hide confidences
+    half=False,  # use FP16 half-precision inference
+):
+    save_img = not nosave and not source.endswith(
+        ".txt"
+    )  # save inference images
+    webcam = (
+        source.isnumeric()
+        or source.endswith(".txt")
+        or source.lower().startswith(
+            ("rtsp://", "rtmp://", "http://", "https://")
+        )
+    )
+
+    # Directories
+    save_dir = increment_path(
+        Path(project) / name, exist_ok=exist_ok
+    )  # increment run
+    (save_dir / "labels" if save_txt else save_dir).mkdir(
+        parents=True, exist_ok=True
+    )  # make dir
+
+    # Initialize
+    set_logging()
+    device = select_device(device)
+    half &= device.type != "cpu"  # half precision only supported on CUDA
+
+    # Load model
+    w = weights[0] if isinstance(weights, list) else weights
+    classify, suffix, suffixes = (
+        False,
+        Path(w).suffix.lower(),
+        [".pt", ".onnx", ".tflite", ".pb", ""],
+    )
+    check_suffix(w, suffixes)  # check weights have acceptable suffix
+    pt, onnx, tflite, pb, saved_model = (
+        suffix == x for x in suffixes
+    )  # backend booleans
+    stride, names = 64, [f"class{i}" for i in range(1000)]  # assign defaults
+    if pt:
+        model = attempt_load(weights, map_location=device)  # load FP32 model
+        stride = int(model.stride.max())  # model stride
+        names = (
+            model.module.names if hasattr(model, "module") else model.names
+        )  # get class names
+        if half:
+            model.half()  # to FP16
+        if classify:  # second-stage classifier
+            modelc = load_classifier(name="resnet50", n=2)  # initialize
+            modelc.load_state_dict(
+                torch.load("resnet50.pt", map_location=device)["model"]
+            ).to(device).eval()
+    elif onnx:
+        check_requirements(("onnx", "onnxruntime"))
+        import onnxruntime
+
+        session = onnxruntime.InferenceSession(w, None)
+    else:  # TensorFlow models
+        check_requirements(("tensorflow>=2.4.1",))
+        import tensorflow as tf
+
+        if (
+            pb
+        ):  # https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
+
+            def wrap_frozen_graph(gd, inputs, outputs):
+                x = tf.compat.v1.wrap_function(
+                    lambda: tf.compat.v1.import_graph_def(gd, name=""), []
+                )  # wrapped import
+                return x.prune(
+                    tf.nest.map_structure(x.graph.as_graph_element, inputs),
+                    tf.nest.map_structure(x.graph.as_graph_element, outputs),
+                )
+
+            graph_def = tf.Graph().as_graph_def()
+            graph_def.ParseFromString(open(w, "rb").read())
+            frozen_func = wrap_frozen_graph(
+                gd=graph_def, inputs="x:0", outputs="Identity:0"
+            )
+        elif saved_model:
+            model = tf.keras.models.load_model(w)
+        elif tflite:
+            interpreter = tf.lite.Interpreter(
+                model_path=w
+            )  # load TFLite model
+            interpreter.allocate_tensors()  # allocate
+            input_details = interpreter.get_input_details()  # inputs
+            output_details = interpreter.get_output_details()  # outputs
+            int8 = (
+                input_details[0]["dtype"] == np.uint8
+            )  # is TFLite quantized uint8 model
+    imgsz = check_img_size(imgsz, s=stride)  # check image size
+    ascii = is_ascii(names)  # names are ascii (use PIL for UTF-8)
+
+    # Dataloader
+    print("Loading data from the source", source)
+    if webcam:
+        view_img = check_imshow()
+        cudnn.benchmark = (
+            True  # set True to speed up constant image size inference
+        )
+        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
+        bs = len(dataset)  # batch_size
+    else:
+        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
+        bs = 1  # batch_size
+    vid_path, vid_writer = [None] * bs, [None] * bs
+
+    # Run inference
+    if pt and device.type != "cpu":
+        model(
+            torch.zeros(1, 3, *imgsz)
+            .to(device)
+            .type_as(next(model.parameters()))
+        )  # run once
+    dt, seen = [0.0, 0.0, 0.0], 0
+    results = []
+    for path, img, im0s, vid_cap in dataset:
+        t1 = time_sync()
+        if onnx:
+            img = img.astype("float32")
+        else:
+            img = torch.from_numpy(img).to(device)
+            img = img.half() if half else img.float()  # uint8 to fp16/32
+        img = img / 255.0  # 0 - 255 to 0.0 - 1.0
+        if len(img.shape) == 3:
+            img = img[None]  # expand for batch dim
+        t2 = time_sync()
+        dt[0] += t2 - t1
+
+        # Inference
+        if pt:
+            visualize = (
+                increment_path(save_dir / Path(path).stem, mkdir=True)
+                if visualize
+                else False
+            )
+            pred = model(img, augment=augment, visualize=visualize)[0]
+        elif onnx:
+            pred = torch.tensor(
+                session.run(
+                    [session.get_outputs()[0].name],
+                    {session.get_inputs()[0].name: img},
+                )
+            )
+        else:  # tensorflow model (tflite, pb, saved_model)
+            imn = img.permute(0, 2, 3, 1).cpu().numpy()  # image in numpy
+            if pb:
+                pred = frozen_func(x=tf.constant(imn)).numpy()
+            elif saved_model:
+                pred = model(imn, training=False).numpy()
+            elif tflite:
+                if int8:
+                    scale, zero_point = input_details[0]["quantization"]
+                    imn = (imn / scale + zero_point).astype(
+                        np.uint8
+                    )  # de-scale
+                interpreter.set_tensor(input_details[0]["index"], imn)
+                interpreter.invoke()
+                pred = interpreter.get_tensor(output_details[0]["index"])
+                if int8:
+                    scale, zero_point = output_details[0]["quantization"]
+                    pred = (
+                        pred.astype(np.float32) - zero_point
+                    ) * scale  # re-scale
+            pred[..., 0] *= imgsz[1]  # x
+            pred[..., 1] *= imgsz[0]  # y
+            pred[..., 2] *= imgsz[1]  # w
+            pred[..., 3] *= imgsz[0]  # h
+            pred = torch.tensor(pred)
+        t3 = time_sync()
+        dt[1] += t3 - t2
+
+        # NMS
+        pred = non_max_suppression(
+            pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det
+        )
+        dt[2] += time_sync() - t3
+
+        # Second-stage classifier (optional)
+        if classify:
+            pred = apply_classifier(pred, modelc, img, im0s)
+
+        # Process predictions
+        for i, det in enumerate(pred):  # per image
+            seen += 1
+            if webcam:  # batch_size >= 1
+                p, s, im0, frame = (
+                    path[i],
+                    f"{i}: ",
+                    im0s[i].copy(),
+                    dataset.count,
+                )
+            else:
+                p, s, im0, frame = (
+                    path,
+                    "",
+                    im0s.copy(),
+                    getattr(dataset, "frame", 0),
+                )
+
+            p = Path(p)  # to Path
+            save_path = str(save_dir / p.name)  # img.jpg
+            txt_path = str(save_dir / "labels" / p.stem) + (
+                "" if dataset.mode == "image" else f"_{frame}"
+            )  # img.txt
+            s += "%gx%g " % img.shape[2:]  # print string
+            gn = torch.tensor(im0.shape)[
+                [1, 0, 1, 0]
+            ]  # normalization gain whwh
+            imc = im0.copy() if save_crop else im0  # for save_crop
+            annotator = Annotator(
+                im0, line_width=line_thickness, pil=not ascii
+            )
+            if len(det):
+                # Rescale boxes from img_size to im0 size
+                det[:, :4] = scale_coords(
+                    img.shape[2:], det[:, :4], im0.shape
+                ).round()
+                results.append((im0, det))
+                # Print results
+                for c in det[:, -1].unique():
+                    n = (det[:, -1] == c).sum()  # detections per class
+                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
+
+                # Write results
+                for *xyxy, conf, cls in reversed(det):
+                    if save_txt:  # Write to file
+                        xywh = (
+                            (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn)
+                            .view(-1)
+                            .tolist()
+                        )  # normalized xywh
+                        line = (
+                            (cls, *xywh, conf) if save_conf else (cls, *xywh)
+                        )  # label format
+                        with open(txt_path + ".txt", "a") as f:
+                            f.write(("%g " * len(line)).rstrip() % line + "\n")
+
+                    if save_img or save_crop or view_img:  # Add bbox to image
+                        c = int(cls)  # integer class
+                        label = (
+                            None
+                            if hide_labels
+                            else (
+                                names[c]
+                                if hide_conf
+                                else f"{names[c]} {conf:.2f}"
+                            )
+                        )
+                        annotator.box_label(xyxy, label, color=colors(c, True))
+                        if save_crop:
+                            save_one_box(
+                                xyxy,
+                                imc,
+                                file=save_dir
+                                / "crops"
+                                / names[c]
+                                / f"{p.stem}.jpg",
+                                BGR=True,
+                            )
+            # Print time (inference-only)
+            print(f"{s}Done. ({t3 - t2:.3f}s)")
+
+            # Stream results
+            im0 = annotator.result()
+            if view_img:
+                cv2.imshow(str(p), im0)
+                cv2.waitKey(1)  # 1 millisecond
+
+            # Save results (image with detections)
+            if save_img:
+                if dataset.mode == "image":
+                    cv2.imwrite(save_path, im0)
+                else:  # 'video' or 'stream'
+                    if vid_path[i] != save_path:  # new video
+                        vid_path[i] = save_path
+                        if isinstance(vid_writer[i], cv2.VideoWriter):
+                            vid_writer[
+                                i
+                            ].release()  # release previous video writer
+                        if vid_cap:  # video
+                            fps = vid_cap.get(cv2.CAP_PROP_FPS)
+                            w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                            h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                        else:  # stream
+                            fps, w, h = 30, im0.shape[1], im0.shape[0]
+                            save_path += ".mp4"
+                        vid_writer[i] = cv2.VideoWriter(
+                            save_path,
+                            cv2.VideoWriter_fourcc(*"mp4v"),
+                            fps,
+                            (w, h),
+                        )
+                    vid_writer[i].write(im0)
+
+    # Print results
+    t = tuple(x / seen * 1e3 for x in dt)  # speeds per image
+    print(
+        f"Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}"
+        % t
+    )
+    return results
+    # if save_txt or save_img:
+    #     s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
+    #     print(f"Results saved to {colorstr('bold', save_dir)}{s}")
+    # if update:
+    #     strip_optimizer(weights)  # update model (to fix SourceChangeWarning)

yolov5s.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1610cfd81f8cab94254b35f6b7da2981fa40f93ad1bd3dd1803c52e7f44753e
+size 14795158