Update app.py

app.py

@@ -44,27 +44,26 @@ class SqueezeNet(nn.Module):
         x = self.avgpool(self.conv10(self.fire9(x)))
         return torch.flatten(x, start_dim=1)
 
-# Initialize the model and load weights
-model = SqueezeNet(out_channels=1)  # Adjust output channels if needed
+model = SqueezeNet(out_channels=1)  
 model.load_state_dict(torch.load("squeezenet.pth", map_location=torch.device('cpu')))
 model.eval()  
 
 transform = transforms.Compose([
-    transforms.Resize((128, 128)),   # Resize to match model's input size
-    transforms.ToTensor(),           # Convert to tensor
-    transforms.Normalize([0.5], [0.5])  # Normalize based on training dataset
+    transforms.Resize((128, 128)),   
+    transforms.ToTensor(),           
+    transforms.Normalize([0.5], [0.5])  
 ])
 
 def classify_brain_tumor(image):
-    image = transform(image).unsqueeze(0)  # Preprocess and add batch dimension
+    image = transform(image).unsqueeze(0)  
     with torch.no_grad():
         output = model(image)
-        prediction = torch.sigmoid(output).item()  # Apply sigmoid for binary classification
+        prediction = torch.sigmoid(output).item()  
     return "Tumor" if prediction >= 0.5 else "No Tumor"
 
 interface = gr.Interface(
     fn=classify_brain_tumor,
-    inputs=gr.inputs.Image(type="pil"),
+    inputs=gr.Image(type="pil"),
     outputs="text",
     title="Brain Tumor Classification",
     description="Upload an MRI image to classify if it has a tumor or not."