Update app.py

app.py

@@ -11,20 +11,19 @@ from pytorch_grad_cam.utils.image import show_cam_on_image
 import os
 import datetime
 
+# -----------------------
 # Setup
+# -----------------------
 device = torch.device("cpu")
 save_dir = "/home/user/app/saved_predictions"
-if not os.path.exists(save_dir):
-    os.makedirs(save_dir)
-    print("📁 Folder created:", save_dir)
 os.makedirs(save_dir, exist_ok=True)
 
-
 # Placeholder image for invalid uploads
 invalid_img = Image.new("RGB", (224, 224), color=(200, 200, 200))
 
-
+# -----------------------
 # Load model
+# -----------------------
 model = models.resnet50(weights=None)
 model.fc = torch.nn.Linear(model.fc.in_features, 2)
 model.load_state_dict(torch.load("resnet50_dr_classifier.pth", map_location=device))
@@ -43,6 +42,9 @@ transform = transforms.Compose([
                          [0.229, 0.224, 0.225])
 ])
 
+# -----------------------
+# Helper: basic fundus check
+# -----------------------
 def looks_like_fundus(image):
     """
     Basic heuristic to check if an image is likely a retinal fundus scan.
@@ -56,6 +58,9 @@ def looks_like_fundus(image):
     # Fundus images usually occupy ~40–75% of the area
     return 0.40 < white_ratio < 0.75
 
+# -----------------------
+# Predict and save
+# -----------------------
 def predict_retinopathy(image):
     # Validate image first
     if not looks_like_fundus(image):
@@ -80,7 +85,10 @@ def predict_retinopathy(image):
     # Grad-CAM
     rgb_img_np = np.array(img).astype(np.float32) / 255.0
     rgb_img_np = np.ascontiguousarray(rgb_img_np)
-    grayscale_cam = cam(input_tensor=img_tensor, targets=[ClassifierOutputTarget(pred)])[0]
+    grayscale_cam = cam(
+        input_tensor=img_tensor,
+        targets=[ClassifierOutputTarget(pred)]
+    )[0]
     cam_image = show_cam_on_image(rgb_img_np, grayscale_cam, use_rgb=True)
     cam_pil = Image.fromarray(cam_image)
 
@@ -88,12 +96,14 @@ def predict_retinopathy(image):
     filename = f"{timestamp}_{label}_{confidence:.2f}.png"
     cam_pil.save(os.path.join(save_dir, filename))
 
-   return (
+    return (
         cam_pil,
         f"{label} (Confidence: {confidence:.2f})"
     )
 
+# -----------------------
 # Gradio app
+# -----------------------
 gr.Interface(
     fn=predict_retinopathy,
     inputs=gr.Image(type="pil", label="Upload Retinal Image"),
@@ -107,8 +117,7 @@ gr.Interface(
         "Upload an image to classify DR and visualise the Grad-CAM heatmap showing important regions."
     ),
     article=(
-        "⚕️ **OpthaDetect** is an AI-powered ophthalmic diagnostic tool. "
+        "⚕️ **OpthaDetect** is an AI-powered ophthalmic decision-support tool. "
         "It highlights retinal risk regions using Grad-CAM for better clinical interpretability."
     )
 ).launch()
-