Update streamlit_app.py

streamlit_app.py

@@ -1,3 +1,6 @@
+import os
+os.environ["STREAMLIT_BROWSER_GATHER_USAGE_STATS"] = "false"  # Prevent Hugging Face write errors
+
 import streamlit as st
 from huggingface_hub import hf_hub_download
 from tensorflow.keras.models import load_model
@@ -9,62 +12,63 @@ from PIL import Image
 @st.cache_resource
 def load_model_from_hf():
     model_path = hf_hub_download(
-        repo_id="1Codephoenix/fish-freshness-model",
+        repo_id="1Codephoenix/fish-freshness-model",  # Your model repo
         filename="fish_freshness_model_retrained_final.keras"
     )
     return load_model(model_path)
 
 model = load_model_from_hf()
 
-# Class labels and custom messages
+# Define class names and interpretation messages
 class_names = ['Fresh', 'Moderately Fresh', 'Spoiled']
 custom_messages = {
     'Fresh': (
         "✅ **Fresh Fish Detected**\n"
         "- Age: Less than 1 day old\n"
-        "- Characteristics: Bright eyes, red gills, firm flesh"
+        "- Bright eyes, red gills, firm flesh"
     ),
     'Moderately Fresh': (
-        "⚠️ **Moderately Fresh**\n"
-        "- Age: 2–3 days\n"
-        "- Characteristics: Slightly dull, odor begins, flesh softens"
+        "⚠️ **Moderately Fresh Fish**\n"
+        "- Age: Around 2–3 days\n"
+        "- Slight odor, some loss of firmness"
     ),
     'Spoiled': (
-        "🚫 **Spoiled Fish**\n"
-        "- Age: 4+ days or treated\n"
-        "- Characteristics: Cloudy eyes, odor, unsafe to eat"
+        "🚫 **Spoiled or Unsafe Fish**\n"
+        "- Age: 4+ days or chemically preserved\n"
+        "- Strong smell, dull eyes, unsafe to eat"
     )
 }
 
 # Streamlit UI
-st.title("🐟 Fish Freshness Classifier")
-st.subheader("Upload an image of a fish to predict its freshness level")
+st.set_page_config(page_title="Fish Freshness Classifier", page_icon="🐟")
+st.title("🐟 AI-Powered Fish Freshness Classifier")
+st.subheader("Upload a fish image to predict its freshness level")
 
-uploaded_file = st.file_uploader("Upload Fish Image", type=["jpg", "jpeg", "png"])
+uploaded_file = st.file_uploader("Choose an image", type=["jpg", "jpeg", "png"])
 
 if uploaded_file:
     try:
         # Load and preprocess the image
         img = Image.open(uploaded_file).convert("RGB")
-        img_resized = img.resize((224, 224))  # Match model input
+        img_resized = img.resize((224, 224))
         img_array = image.img_to_array(img_resized)
-        img_array = np.expand_dims(img_array / 255.0, axis=0)  # Normalize
+        img_array = np.expand_dims(img_array / 255.0, axis=0)
 
-        # Predict
+        # Predict using the model
         prediction = model.predict(img_array)
         predicted_index = np.argmax(prediction)
         predicted_class = class_names[predicted_index]
         confidence = prediction[0][predicted_index]
 
-        # Show image and result
+        # Display results
         st.image(img, caption="Uploaded Fish Image", use_column_width=True)
         st.markdown(f"### 🎯 Prediction: **{predicted_class}** ({confidence * 100:.2f}% confidence)")
         st.markdown(custom_messages[predicted_class])
 
         # Show all class probabilities
-        st.subheader("📊 Confidence Scores")
-        for i, class_name in enumerate(class_names):
-            st.write(f"- {class_name}: {prediction[0][i]*100:.2f}%")
+        st.subheader("📊 Class Probabilities:")
+        for i, name in enumerate(class_names):
+            st.write(f"- {name}: {prediction[0][i] * 100:.2f}%")
 
     except Exception as e:
-        st.error(f"⚠️ Error processing image: {e}")
+        st.error(f"❌ Error processing image: {e}")