Update app.py

app.py

@@ -80,12 +80,13 @@ def classifyCar(im):
     boxes = list(outputs["instances"].pred_boxes[car_class_true])
     max_idx = torch.tensor([(x[2] - x[0])*(x[3] - x[1]) for x in boxes]).argmax().item()
     
-    im2 = Image.fromarray(np.uint8(out.get_image())).convert('RGB').crop(boxes[max_idx].to(torch.int64).numpy())
+    im2 = Image.fromarray(np.uint8(im)).convert('RGB').crop(boxes[max_idx].to(torch.int64).numpy())
     
     carTransforms = transforms.Compose([transforms.Resize((224, 224))])
     im2 = carTransforms(im2)
 
     label = "success"
+    img = Image.toarray(im2)
   except:
     label = "fail2"
     #im2 = carTransforms(im).unsqueeze(0)  # transform and add batch dimension
@@ -93,12 +94,12 @@ def classifyCar(im):
     #  scores = torch.nn.functional.softmax(DesignModernityModel(im2)[0])
       #{LABELS[i]: float(scores[i]) for i in range(n_labels)}
       #Image.fromarray(np.uint8(out.get_image())).convert('RGB')
-  return label
+  return label, img
 
 #examples = [[example_img.jpg], [example_img2.jpg]]  # must be uploaded in repo
 
 # create interface for model
-interface = gr.Interface(classifyCar, inputs='image', outputs=['label'], cache_examples=False, title='VW Up or Fiat 500')
+interface = gr.Interface(classifyCar, inputs='image', outputs=['image','label'], cache_examples=False, title='VW Up or Fiat 500')
 interface.launch()