Update app.py

app.py

@@ -84,15 +84,31 @@ with gr.Blocks() as demo:
       nms_boxes_output = []
 
       # process the input image for inference/gradcam
-      input_img = cv2.resize(input_img, (416, 416))
-      input_img_copy = input_img.copy()
-      input_img = np.float32(input_img) / 255
+      # input_img = cv2.resize(input_img, (416, 416))
+      # input_img_copy = input_img.copy()
+      # input_img = np.float32(input_img) / 255
+      # transform = transforms.ToTensor()
+      # input_img = transform(input_img).unsqueeze(0)
+
+     # image transformation
+      test_transforms = Al.Compose(
+        [
+            Al.LongestMaxSize(max_size=416),
+            Al.PadIfNeeded(
+                min_height=416, min_width=416, border_mode=cv2.BORDER_CONSTANT
+            ),
+            Al.Normalize(mean=[0, 0, 0], std=[1, 1, 1], max_pixel_value=255,),
+            #ToTensorV2(),
+        ]
+      )
+        
+      input_img_copy = test_transforms(image=input_img)['image']
       transform = transforms.ToTensor()
-      input_img = transform(input_img).unsqueeze(0)
+      input_img_tensor = transform(input_img_copy).unsqueeze(0)
 
       # infer the image
       inference_model.eval()
-      test_img_out   = inference_model(input_img)
+      test_img_out   = inference_model(input_img_tensor)
 
       # process the outputs to create bounding boxes
       for i in range(3):
@@ -124,13 +140,13 @@ with gr.Blocks() as demo:
 
         target_layers = [inference_model.model]
         cam = EigenCAM(inference_model, target_layers, use_cuda=False,reshape_transform=yolov3_reshape_transform)
-        grayscale_cam = cam(input_tensor = input_img, targets= targets)
+        grayscale_cam = cam(input_tensor = input_img_tensor, targets= targets)
         grayscale_cam = grayscale_cam[0, :]
-        visualization = show_cam_on_image(input_img_copy/255, grayscale_cam, use_rgb=True, image_weight=gradcam_opa)
+        visualization = show_cam_on_image(input_img_copy, grayscale_cam, use_rgb=True, image_weight=gradcam_opa)
 
         return (visualization,sections)
       else:
-        return (np.array(input_img.squeeze(0).permute(1,2,0)),sections)
+        return (np.array(input_img_tensor.squeeze(0).permute(1,2,0)),sections)
 
     # app GUI
     with gr.Row():