Update app.py

app.py

@@ -49,9 +49,9 @@ condition_details = {
     "Diverticulitis": {"description": "Inflammation of diverticula in the colon.", "recommendation": "Gastroenterology consultation."}
 }
 
-# Load model (using a smaller model like MobileNetV2 for faster inference)
-model = models.mobilenet_v2(pretrained=True)
-model.classifier[1] = torch.nn.Linear(model.classifier[1].in_features, len(conditions))  # Adjust the classifier for our condition count
+# Load model (using a specialized X-ray model or pre-trained general model)
+model = models.densenet121(pretrained=True)  # You can swap to a more specific X-ray model if available
+model.classifier = torch.nn.Linear(model.classifier.in_features, len(conditions))  # Adjust the classifier for our condition count
 model.eval()
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)
@@ -59,9 +59,9 @@ model.to(device)
 # Image preprocessing
 def preprocess_image(image):
     transform = transforms.Compose([
-        transforms.Resize((224, 224)),
+        transforms.Resize((224, 224)),  # Resize to match the model input size
         transforms.ToTensor(),
-        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])  # Standardize based on ImageNet values
     ])
     return transform(image).unsqueeze(0).to(device)