Update app.py

app.py

@@ -1,22 +1,3 @@
-import streamlit as st
-from tensorflow import keras
-import numpy as np
-from huggingface_hub import HfFileSystem
-from PIL import Image
-
-# Authenticate and download the custom model from Hugging Face Spaces
-fs = HfFileSystem()
-model_path = 'dhhd255/main_model/best_model.h5'
-with fs.open(model_path, 'rb') as f:
-    model_content = f.read()
-
-# Save the model file to disk
-with open('best_model.h5', 'wb') as f:
-    f.write(model_content)
-
-# Load your custom model
-model = keras.models.load_model('best_model.h5')
-
 # Define a function that takes an image as input and uses the model for inference
 def image_classifier(image):
     # Preprocess the input image
@@ -31,13 +12,15 @@ def image_classifier(image):
     # Use your custom model for inference
     predictions = model.predict(image)
     
-    # Process the predictions and return the result
-    result = {}
-    for i, prediction in enumerate(predictions[0]):
-        label = f'Label {i+1}'
-        result[label] = prediction
+    # Get the index of the highest predicted probability
+    predicted_index = np.argmax(predictions[0])
+    
+    # Map the index to a class label
+    labels = ['Healthy', 'Parkinson']
+    predicted_label = labels[predicted_index]
     
-    return result
+    # Return the result
+    return predictions[0], predicted_label
 
 # Create a Streamlit app with an image upload input
 uploaded_file = st.file_uploader('Upload an image')
@@ -47,5 +30,8 @@ if uploaded_file is not None:
     image = np.array(image)
     
     # Use the image for inference
-    result = image_classifier(image)
-    st.write(result)
+    predictions, predicted_label = image_classifier(image)
+    
+    # Display the result
+    st.write(f'Predictions: {predictions}')
+    st.write(f'Predicted label: {predicted_label}')