Update app.py

app.py

@@ -14,11 +14,14 @@ def predict_regression(image):
     # Preprocess image
     image = Image.fromarray(image.astype('uint8'))  # Convert numpy array to PIL image
     image = image.resize((150, 150))
-    image = image.convert('L')#resize the image to 28x28 and converts it to gray scale
-    image = np.array(image)
-    print(image.shape)
+    # If model expects RGB, convert to RGB
+    image = image.convert('RGB')  # Ensure image is in RGB format
+    image = np.array(image, dtype=np.float32)  # Convert image to float32
+    image /= 255.0  # Normalize image data to 0-1 range
+
+    print(image.shape)  # Debugging: Check the shape to ensure it's correct
     # Predict
-    prediction = model.predict(image[None, ...])  # Assuming single regression value
+    prediction = model.predict(image[None, ...])  # Adjusted to include batch dimension properly
     confidences = {labels[i]: np.round(float(prediction[0][i]), 2) for i in range(len(labels))}
     return confidences
 
@@ -28,6 +31,6 @@ output_text = gr.Textbox(label="Predicted Value")
 interface = gr.Interface(fn=predict_regression, 
                          inputs=input_image, 
                          outputs=gr.Label(),
-                         examples=["images/Aerodactyl.png", "images/arbok.jpg", "images/Alakazam.png", "images/abra.gif","images/Arcanine.png"],   
-                         description="A simple mlp classification model for image classification using the mnist dataset.")
-interface.launch()
+                         examples=["images/Aerodactyl.png", "images/arbok.jpg", "images/Alakazam.png", "images/abra.gif", "images/Arcanine.png"],   
+                         description="A simple mlp classification model for image classification using a few pokemons.")
+interface.launch()