add try it inference for hockey breeds

requirements-cpu.txt

@@ -0,0 +1,91 @@
+altair==5.4.1
+annotated-types==0.7.0
+attrs==24.2.0
+blinker==1.8.2
+blis==0.7.11
+cachetools==5.5.0
+catalogue==2.0.10
+certifi==2024.8.30
+charset-normalizer==3.3.2
+click==8.1.7
+cloudpathlib==0.19.0
+confection==0.1.5
+contourpy==1.3.0
+cycler==0.12.1
+cymem==2.0.8
+fastai==2.7.17
+fastcore==1.7.4
+fastdownload==0.0.7
+fastprogress==1.0.3
+filelock==3.13.1
+fonttools==4.53.1
+fsspec==2024.2.0
+gitdb==4.0.11
+GitPython==3.1.43
+huggingface-hub==0.24.6
+idna==3.8
+Jinja2==3.1.4
+joblib==1.4.2
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.7
+langcodes==3.4.0
+language_data==1.2.0
+marisa-trie==1.2.0
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.2
+mdurl==0.1.2
+mpmath==1.3.0
+murmurhash==1.0.10
+narwhals==1.6.0
+networkx==3.2.1
+numpy==1.26.4
+packaging==24.1
+pandas==2.2.2
+pillow==10.4.0
+preshed==3.0.9
+protobuf==5.28.0
+pyarrow==17.0.0
+pydantic==2.9.0
+pydantic_core==2.23.2
+pydeck==0.9.1
+Pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+pytz==2024.1
+PyYAML==6.0.2
+referencing==0.35.1
+requests==2.32.3
+rich==13.8.0
+rpds-py==0.20.0
+scikit-learn==1.5.1
+scipy==1.14.1
+shellingham==1.5.4
+six==1.16.0
+smart-open==7.0.4
+smmap==5.0.1
+spacy==3.7.6
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+srsly==2.4.8
+streamlit==1.38.0
+streamlit-image-select==0.6.0
+sympy==1.12
+tenacity==8.5.0
+thinc==8.2.5
+threadpoolctl==3.5.0
+toml==0.10.2
+torch==2.4.1+cpu
+torchaudio==2.4.1+cpu
+torchvision==0.19.1+cpu
+tornado==6.4.1
+tqdm==4.66.5
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.2
+wasabi==1.1.3
+watchdog==4.0.2
+weasel==0.4.1
+wrapt==1.16.0

src/Hockey_Breeds.py

@@ -1,7 +1,35 @@
 import streamlit as st
 from streamlit_image_select import image_select
+import zip_files
 
+import random
 import logging
+from huggingface_hub import from_pretrained_fastai
+
+@st.cache_resource
+def get_model():
+    repo_id = "danbiagini/hockey_breeds"
+    return from_pretrained_fastai(repo_id)
+
+def classify_image(learn, img):
+    categories = ('Hockey Goalie', 'Hockey Player', "Hockey Referee")
+    pred,idx,prob = learn.predict(img)
+    return dict(zip(categories, map(float, prob)))
+
+def reroll_sample_images():
+    # unzip the sample images
+    players = zip_files.extract_files_from_zip("src/images/samples/player-samples.zip")
+    goalies = zip_files.extract_files_from_zip("src/images/samples/goalie-samples.zip")
+    referees = zip_files.extract_files_from_zip("src/images/samples/referee-samples.zip")
+
+    #randomize a single file from players, goalies and referee for samples
+    st.session_state.sample = dict()
+    st.session_state.sample["player"] = players[list(players.keys())[random.randint(0, len(players) - 1)]]
+    st.session_state.sample["goalie"] = goalies[list(goalies.keys())[random.randint(0, len(goalies) - 1)]]
+    st.session_state.sample["referee"] = referees[list(referees.keys())[random.randint(0, len(referees) - 1)]]
+
+if 'sample' not in st.session_state:
+    reroll_sample_images()
 
 st.set_page_config(page_title='Hockey Breeds', layout="wide",
                    page_icon=":frame_with_picture:")
@@ -22,13 +50,27 @@ desc = '''This "Hockey Breeds" model was built using 50 hockey related images fo
 The total training time for this was approximately 5 minutes running on a low-end GPU. It’s impressive how accurate this quick / small model can be!'''
 
 st.markdown(desc)
-
+st.image("src/images/samples/sampl_batch.png")
 st.subheader("Validation Results")
 st.markdown('Validation of the model\'s performance was done using 26 images not included in the training set.  The model performed fairly well against the validation dataset, with only 1 misclassified image.')
-st.image("src/images/samples/confusion_matrix.png", caption="Confusion Matrix for Hockey Breeds ")
+st.image("src/images/artifacts/confusion_matrix.png", caption="Confusion Matrix for Hockey Breeds ")
+
+st.subheader("Try It Out")
+
+img = image_select(label="Select an image and hockey breeds will guess a label", images=list(st.session_state.sample.values()))
 
-st.subheader("Try it out")
+st.button("Re-roll Samples", on_click=reroll_sample_images)
 
-# unzip the sample images
+model = get_model()
 
-img = image_select(label="Select an image and hockey breeds will guess a label", images=["src/images/"])
+if img:
+    res = classify_image(model, img)
+    # Sort the dictionary items by value in descending order
+    max = 0
+    max_label = ""
+    for k,v in res.items():
+        prob = round(v*100, 2)
+        if prob > max:
+            max = prob
+            max_label = k
+    st.metric(label=max_label, value=max)