m-aliabbas1 commited on
Commit
fbef8bb
1 Parent(s): 1766a1a

readme update 2

Browse files
Files changed (1) hide show
  1. README.md +42 -164
README.md CHANGED
@@ -8,196 +8,74 @@ metrics:
8
  pipeline_tag: image-text-to-text
9
  ---
10
 
11
- # Model Card for Model ID
12
 
 
13
 
14
 
 
15
 
16
- ## Model Details
17
 
18
- ### Model Description
19
 
20
- <!-- Provide a longer summary of what this model is. -->
 
 
21
 
22
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
23
-
24
- - **Developed by:** [More Information Needed]
25
- - **Funded by [optional]:** [More Information Needed]
26
- - **Shared by [optional]:** [More Information Needed]
27
- - **Model type:** [More Information Needed]
28
- - **Language(s) (NLP):** [More Information Needed]
29
- - **License:** [More Information Needed]
30
- - **Finetuned from model [optional]:** [More Information Needed]
31
-
32
- ### Model Sources [optional]
33
-
34
- <!-- Provide the basic links for the model. -->
35
-
36
- - **Repository:** [More Information Needed]
37
- - **Paper [optional]:** [More Information Needed]
38
- - **Demo [optional]:** [More Information Needed]
39
-
40
- ## Uses
41
-
42
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
43
-
44
- ### Direct Use
45
-
46
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
47
-
48
- [More Information Needed]
49
-
50
- ### Downstream Use [optional]
51
-
52
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
53
-
54
- [More Information Needed]
55
-
56
- ### Out-of-Scope Use
57
-
58
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
59
-
60
- [More Information Needed]
61
-
62
- ## Bias, Risks, and Limitations
63
-
64
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
65
-
66
- [More Information Needed]
67
-
68
- ### Recommendations
69
-
70
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
71
-
72
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
73
-
74
- ## How to Get Started with the Model
75
-
76
- Use the code below to get started with the model.
77
-
78
- [More Information Needed]
79
-
80
- ## Training Details
81
-
82
- ### Training Data
83
-
84
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
85
-
86
- [More Information Needed]
87
-
88
- ### Training Procedure
89
-
90
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
91
-
92
- #### Preprocessing [optional]
93
-
94
- [More Information Needed]
95
 
 
96
 
97
- #### Training Hyperparameters
98
 
99
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
 
100
 
101
- #### Speeds, Sizes, Times [optional]
102
 
103
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
104
 
105
- [More Information Needed]
106
 
107
- ## Evaluation
 
 
108
 
109
- <!-- This section describes the evaluation protocols and provides the results. -->
110
 
111
- ### Testing Data, Factors & Metrics
112
 
113
- #### Testing Data
 
 
 
114
 
115
- <!-- This should link to a Dataset Card if possible. -->
116
 
117
- [More Information Needed]
118
 
119
- #### Factors
 
 
 
120
 
121
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
122
 
123
- [More Information Needed]
124
 
125
- #### Metrics
126
 
127
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
 
 
128
 
129
- [More Information Needed]
130
 
131
- ### Results
132
 
133
- [More Information Needed]
134
-
135
- #### Summary
136
-
137
-
138
-
139
- ## Model Examination [optional]
140
-
141
- <!-- Relevant interpretability work for the model goes here -->
142
-
143
- [More Information Needed]
144
-
145
- ## Environmental Impact
146
-
147
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
148
-
149
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
150
-
151
- - **Hardware Type:** [More Information Needed]
152
- - **Hours used:** [More Information Needed]
153
- - **Cloud Provider:** [More Information Needed]
154
- - **Compute Region:** [More Information Needed]
155
- - **Carbon Emitted:** [More Information Needed]
156
-
157
- ## Technical Specifications [optional]
158
-
159
- ### Model Architecture and Objective
160
-
161
- [More Information Needed]
162
-
163
- ### Compute Infrastructure
164
-
165
- [More Information Needed]
166
-
167
- #### Hardware
168
-
169
- [More Information Needed]
170
-
171
- #### Software
172
-
173
- [More Information Needed]
174
-
175
- ## Citation [optional]
176
-
177
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
178
-
179
- **BibTeX:**
180
-
181
- [More Information Needed]
182
-
183
- **APA:**
184
-
185
- [More Information Needed]
186
-
187
- ## Glossary [optional]
188
-
189
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
190
-
191
- [More Information Needed]
192
-
193
- ## More Information [optional]
194
-
195
- [More Information Needed]
196
-
197
- ## Model Card Authors [optional]
198
-
199
- [More Information Needed]
200
 
201
- ## Model Card Contact
 
 
 
202
 
203
- [More Information Needed]
 
8
  pipeline_tag: image-text-to-text
9
  ---
10
 
11
+ # Florence-2 Fine-Tuning with PathVQA
12
 
13
+ This document provides an overview of fine-tuning the Florence-2 model with the PathVQA dataset. Florence-2 is a sequence-to-sequence model that excels in various computer vision tasks by leveraging its robust architecture and extensive pre-training dataset.
14
 
15
 
16
+ ## Florence-2 Model Overview
17
 
18
+ Florence-2 formulates computer vision problems as sequence-to-sequence tasks. The model takes images and text as inputs and generates text as output. Below is a detailed breakdown of the model and its components:
19
 
20
+ ### Model Architecture
21
 
22
+ - **DaViT Vision Encoder**: Converts images into visual embeddings.
23
+ - **BERT Text Encoder**: Converts text prompts into text and location embeddings.
24
+ - **Transformer Architecture**: A standard encoder-decoder transformer processes the embeddings to generate text and location tokens.
25
 
26
+ ### Strength of Florence-2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
 
28
+ The model's strength lies not in its architecture but in the extensive dataset it was pre-trained on. The authors created the FLD-5B dataset to address the limitations of existing datasets like WIT and SA-1B, which contain limited information.
29
 
30
+ ### FLD-5B Dataset
31
 
32
+ - **Content**: Over 5 billion annotations for 126 million images, including boxes, masks, captions, and grounding.
33
+ - **Creation Process**: Largely automated using off-the-shelf task-specific models and a set of heuristics and quality checks to clean the obtained results.
34
 
35
+ ## PathVQA Dataset
36
 
37
+ PathVQA is a dataset of question-answer pairs on pathology images, intended for training and testing Medical Visual Question Answering (VQA) systems. It includes both open-ended questions and binary "yes/no" questions.
38
 
39
+ ### Source
40
 
41
+ The dataset is built from two publicly available pathology textbooks:
42
+ - "Textbook of Pathology"
43
+ - "Basic Pathology"
44
 
45
+ Additionally, images were sourced from the "Pathology Education Informational Resource" (PEIR) digital library. The copyrights of images and captions belong to the publishers and authors of these two books and the owners of the PEIR digital library.
46
 
47
+ ### Dataset Summary
48
 
49
+ - **Total Images**: 5,004
50
+ - **Total Question-Answer Pairs**: 32,795
51
+ - **Referenced Images**: 4,289
52
+ - **Unused Images**: 715
53
 
54
+ After removing duplicate image-question-answer triplets, the dataset contains 32,632 question-answer pairs on 4,289 images.
55
 
56
+ ### Supported Tasks and Leaderboards
57
 
58
+ The PathVQA dataset has an active leaderboard on Papers with Code, ranking models based on:
59
+ - **Yes/No Accuracy**: Accuracy of generated answers for binary "yes/no" questions.
60
+ - **Free-form Accuracy**: Accuracy of generated answers for open-ended questions.
61
+ - **Overall Accuracy**: Accuracy of generated answers across all questions.
62
 
63
+ ## Fine-Tuning Florence-2 with PathVQA
64
 
65
+ The Florence-2 model was fine-tuned using the PathVQA dataset to adapt it for medical visual question answering tasks.
66
 
67
+ ### Methodology
68
 
69
+ 1. **Dataset Preparation**: The PathVQA dataset was obtained from the updated Google Drive link shared by the authors on February 15, 2023.
70
+ 2. **Data Cleaning**: Duplicate image-question-answer triplets were removed.
71
+ 3. **Fine-Tuning**: The model was fine-tuned for seven epochs with the training set.
72
 
 
73
 
 
74
 
75
+ This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
 
77
+ - **Developed by:** Mohammed Ali Abbas
78
+ - **Model type:** VQA
79
+ - **License:** [More Information Needed]
80
+ - **Finetuned from model [optional]:** [More Information Needed]
81