Update app.py

app.py

@@ -1,13 +1,14 @@
 import gradio as gr
-import json
 import torch
 from torch import nn
 from torchvision import models, transforms
 from huggingface_hub import hf_hub_download
 from PIL import Image
-import requests
 import os
-from io import BytesIO
+import logging
+
+# Setup logging
+logging.basicConfig(level=logging.INFO)
 
 # Define the number of classes
 num_classes = 2
@@ -37,49 +38,43 @@ transform = transforms.Compose([
     transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
 ])
 
-# Function to predict from image content
+# Prediction function for an uploaded image
 def predict_from_image(image):
-    # Ensure the image is a PIL Image
-    if not isinstance(image, Image.Image):
-        raise ValueError("Invalid image format received. Please provide a valid image.")
+    try:
+        # Ensure the input is a valid PIL image
+        if not isinstance(image, Image.Image):
+            raise ValueError("Invalid image format received. Please provide a valid image.")
 
-    # Apply transformations
-    image_tensor = transform(image).unsqueeze(0)
+        # Log the input for debugging
+        logging.info("Received image for prediction")
 
-    # Predict
-    with torch.no_grad():
-        outputs = model(image_tensor)
-        predicted_class = torch.argmax(outputs, dim=1).item()
+        # Apply transformations
+        image_tensor = transform(image).unsqueeze(0)
 
-    # Interpret the result
-    if predicted_class == 0:
-        return {"result": "The photo is of fall army worm with problem ID 126."}
-    elif predicted_class == 1:
-        return {"result": "The photo is of a healthy maize image."}
-    else:
-        return {"error": "Unexpected class prediction."}
+        # Predict
+        with torch.no_grad():
+            outputs = model(image_tensor)
+            predicted_class = torch.argmax(outputs, dim=1).item()
 
-# Function to predict from URL
-def predict_from_url(url):
-    try:
-        response = requests.get(url)
-        response.raise_for_status()  # Ensure the request was successful
-        image = Image.open(BytesIO(response.content))
-        return predict_from_image(image)
+        # Interpret the result
+        if predicted_class == 0:
+            return {"result": "The photo is of fall army worm with problem ID 126."}
+        elif predicted_class == 1:
+            return {"result": "The photo is of a healthy maize image."}
+        else:
+            return {"error": "Unexpected class prediction."}
     except Exception as e:
-        return {"error": f"Failed to process the URL: {str(e)}"}
+        logging.error(f"Error during prediction: {str(e)}")
+        return {"error": f"Failed to process the image: {str(e)}"}
 
-# Gradio interface
+# Gradio interface restricted to image input
 iface = gr.Interface(
-    fn=lambda image, url: predict_from_image(image) if image else predict_from_url(url),
-    inputs=[
-        gr.Image(type="pil", label="Upload an Image"),
-        gr.Textbox(label="Or Enter an Image URL", placeholder="Provide a valid image URL"),
-    ],
+    fn=predict_from_image,  # Only handle image input
+    inputs=gr.Image(type="pil", label="Upload an Image"),  # Restrict input to image upload
     outputs=gr.JSON(label="Prediction Result"),
     live=True,
     title="Maize Anomaly Detection",
-    description="Upload an image or provide a URL to detect anomalies in maize crops.",
+    description="Upload an image to detect anomalies in maize crops.",
 )
 
 # Launch the interface