Update handler.py

handler.py

@@ -1,5 +1,5 @@
 from typing import Dict, List, Any
-from transformers import DonutProcessor, VisionEncoderDecoderModel
+from transformers import AutoImageProcessor, Swin2SRForImageSuperResolution
 import torch
 
 
@@ -10,37 +10,23 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 class EndpointHandler:
     def __init__(self, path=""):
         # load the model
-        self.processor = DonutProcessor.from_pretrained(path)
-        self.model = VisionEncoderDecoderModel.from_pretrained(path)
+        self.processor = AutoImageProcessor.from_pretrained("caidas/swin2SR-classical-sr-x2-64")
+        self.model = Swin2SRForImageSuperResolution.from_pretrained("caidas/swin2SR-classical-sr-x2-64")
         # move model to device
         self.model.to(device)
-        self.decoder_input_ids = self.processor.tokenizer(
-            "<s_cord-v2>", add_special_tokens=False, return_tensors="pt"
-        ).input_ids
-
-    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
-
-        inputs = data.pop("inputs", data)
-
-
-        # preprocess the input
-        pixel_values = self.processor(inputs, return_tensors="pt").pixel_values
-
-        # forward pass
-        outputs = self.model.generate(
-            pixel_values.to(device),
-            decoder_input_ids=self.decoder_input_ids.to(device),
-            max_length=self.model.decoder.config.max_position_embeddings,
-            early_stopping=True,
-            pad_token_id=self.processor.tokenizer.pad_token_id,
-            eos_token_id=self.processor.tokenizer.eos_token_id,
-            use_cache=True,
-            num_beams=1,
-            bad_words_ids=[[self.processor.tokenizer.unk_token_id]],
-            return_dict_in_generate=True,
-        )
-        # process output
-        prediction = self.processor.batch_decode(outputs.sequences)[0]
-        prediction = self.processor.token2json(prediction)
-
-        return prediction
+
+    def __call__(self, image: Any) -> List[List[Dict[str, float]]]:
+
+        inputs = self.processor(image, return_tensors="pt")
+        outputs = self.model(**inputs)
+        
+        output = outputs.reconstruction.data.squeeze().float().cpu().clamp_(0, 1).numpy()
+        output = np.moveaxis(output, source=0, destination=-1)
+        output = (output * 255.0).round().astype(np.uint8)
+
+        img = Image.fromarray(output)
+        buffered = BytesIO()
+        img.save(buffered, format="JPEG")
+        img_str = base64.b64encode(buffered.getvalue())
+
+        return img_str