Remove image resizing

handler.py

@@ -64,9 +64,6 @@ class EndpointHandler():
         
         # 4. Process and select the best mask
         try:
-            # Get original image dimensions
-            original_height, original_width = img.size[1], img.size[0]
-            
             # Get predicted masks and scores
             predicted_masks = outputs.pred_masks.cpu()
             iou_scores = outputs.iou_scores.cpu()[0]
@@ -75,31 +72,17 @@ class EndpointHandler():
             if predicted_masks.ndim == 5:
                 predicted_masks = predicted_masks.squeeze(1)
             
-            # Resize masks to standard size first
-            predicted_masks = torch.nn.functional.interpolate(
-                predicted_masks,
-                size=(1024, 1024),
-                mode='bilinear',
-                align_corners=False
-            )
-            
             # Select the best mask
             best_mask_idx = torch.argmax(iou_scores)
             best_mask = predicted_masks[0, best_mask_idx, :, :]
             
-            # Resize to original image dimensions
-            final_mask = torch.nn.functional.interpolate(
-                best_mask.unsqueeze(0).unsqueeze(0),
-                size=(original_height, original_width),
-                mode='bilinear',
-                align_corners=False
-            ).squeeze()
-            
-            # Convert to binary mask
-            mask_binary = (final_mask > 0.0).numpy().astype(np.uint8) * 255
+            # Convert to binary mask (no resizing needed since processor doesn't resize)
+            mask_binary = (best_mask > 0.0).numpy().astype(np.uint8) * 255
         
         except Exception as e:
             print("Error processing masks: {}".format(e))
+            # Fallback: create a simple mask
+            height, width = img.size[1], img.size[0]
             mask_binary = np.zeros((height, width), dtype=np.uint8)
             center_x, center_y = width // 2, height // 2
             size = min(width, height) // 8