Updated handler.py

handler.py

@@ -28,23 +28,16 @@ class EndpointHandler:
             A :obj:`dict`:. The object returned should be a dict of one list like {"captions": ["A hugging face at the office"]} containing :
                 - "caption": A string corresponding to the generated caption.
         """
+        
         inputs = data.pop("inputs", data)
         parameters = data.pop("parameters", {})
  
         raw_images = Image.open(BytesIO(inputs))
-
-        inputs = self.processor(inputs, return_tensors="pt").to("cuda")
                                      
         processed_image = self.processor(images=raw_images, return_tensors="pt").to(device)
 
         out = self.model.generate(**processed_image)
-        # processed_image["pixel_values"] = processed_image["pixel_values"].to(device)
-        # processed_image = {**processed_image, **parameters}
-        
-        # with torch.no_grad():
-        #     out = self.model.generate(
-        #         **processed_image
-        #     )
+       
         captions = self.processor.decode(out[0], skip_special_tokens=True)
 
         # postprocess the prediction