Download src/streamlit_app.py from EnYa32/LargeFishClassifcationResNet50: direct link, hf CLI and curl.
- Browser
- Download file 3.21 kB
-
https://huggingface.co/spaces/EnYa32/LargeFishClassifcationResNet50/resolve/main/src/streamlit_app.py
- Command line
-
hf download hf://spaces/EnYa32/LargeFishClassifcationResNet50/src/streamlit_app.py
-
curl -L -o streamlit_app.py https://huggingface.co/spaces/EnYa32/LargeFishClassifcationResNet50/resolve/main/src/streamlit_app.py
3.21 kB
| # --- Fish Classifier using Transfer Learning (ResNet50) | |
| import streamlit as st | |
| import numpy as np | |
| from PIL import Image | |
| import tensorflow as tf | |
| from tensorflow.keras.applications.resnet50 import preprocess_input, ResNet50 | |
| from tensorflow.keras.models import Sequential | |
| from tensorflow.keras.layers import GlobalAveragePooling2D, Dense, Dropout | |
| import warnings | |
| warnings.filterwarnings("ignore", category=DeprecationWarning) | |
| st.set_page_config( | |
| page_title="Fish Classifier (ResNet50 β Transfer Learning)", | |
| layout="centered" | |
| ) | |
| # ------------------ SETTINGS ------------------ | |
| MODEL_PATH = "src/best_fish_resnet50.keras" | |
| IMG_SIZE = (224, 224) | |
| CLASS_NAMES = [ | |
| "Black Sea Sprat", | |
| "Gilt-Head Bream", | |
| "Horse Mackerel", | |
| "Red Mullet", | |
| "Red Sea Bream", | |
| "Sea Bass", | |
| "Shrimp", | |
| "Striped Red Mullet", | |
| "Trout" | |
| ] | |
| # ------------------ LOAD MODEL ------------------ | |
| def load_model_cached(): | |
| base_model = ResNet50( | |
| weights="imagenet", | |
| include_top=False, | |
| input_shape=(IMG_SIZE[0], IMG_SIZE[1], 3) | |
| ) | |
| base_model.trainable = False | |
| model = Sequential([ | |
| base_model, | |
| GlobalAveragePooling2D(), | |
| Dense(256, activation="relu"), | |
| Dropout(0.5), | |
| Dense(len(CLASS_NAMES), activation="softmax") | |
| ]) | |
| model.load_weights(MODEL_PATH) | |
| return model | |
| model = load_model_cached() | |
| # ------------------ IMAGE PREPROCESSING ------------------ | |
| def preprocess_image(image: Image.Image) -> np.ndarray: | |
| image = image.convert("RGB") | |
| image = image.resize(IMG_SIZE) | |
| img_array = np.array(image) | |
| img_array = np.expand_dims(img_array, axis=0) | |
| img_array = preprocess_input(img_array) | |
| return img_array | |
| # ------------------ PREDICTION ------------------ | |
| def predict(image: Image.Image): | |
| processed_img = preprocess_image(image) | |
| preds = model.predict(processed_img) | |
| probs = tf.nn.softmax(preds[0]).numpy() | |
| top_idx = np.argmax(probs) | |
| return CLASS_NAMES[top_idx], probs[top_idx], probs | |
| # ------------------ STREAMLIT UI ------------------ | |
| st.title("π Fish Classifier (Transfer Learning β ResNet50)") | |
| st.write( | |
| "This app uses a **ResNet50 Transfer Learning model** trained on 9 fish species " | |
| "from the *Large Scale Fish Dataset*." | |
| ) | |
| st.sidebar.header("π§ Model Info") | |
| st.sidebar.write(f"**Model file:** `{MODEL_PATH}`") | |
| st.sidebar.write("**Class labels:**") | |
| for cls in CLASS_NAMES: | |
| st.sidebar.write(f"- {cls}") | |
| uploaded_file = st.file_uploader("π€ Upload a fish image", type=["jpg", "jpeg", "png"]) | |
| if uploaded_file is not None: | |
| image = Image.open(uploaded_file) | |
| st.image(image, caption="πΈ Uploaded Image", use_container_width=True) | |
| if st.button("π Predict (ResNet50)"): | |
| with st.spinner("Analyzing..."): | |
| top_class, top_prob, probabilities = predict(image) | |
| st.subheader("π Prediction") | |
| st.write(f"**Class:** `{top_class}`") | |
| st.write(f"**Confidence:** {top_prob:.2%}") | |
| st.subheader("π Confidence per Class") | |
| for cls, prob in zip(CLASS_NAMES, probabilities): | |
| st.write(f"- **{cls}** β {prob:.2%}") | |
| else: | |
| st.info("Upload an image to start.") | |