Update app.py

app.py

@@ -57,7 +57,7 @@ def process_image(image):
     encoding = processor(image, truncation=True, padding="max_length", max_length=512, return_tensors="pt")
     input_ids = encoding.input_ids.to(device)
     attention_mask = encoding.attention_mask.to(device)
-    bbox = encoding.bbox.to(device)
+    bbox = encoding.bbox[0].tolist()
 
     # Inference
     outputs = model(input_ids=input_ids, bbox=bbox, attention_mask=attention_mask)
@@ -65,7 +65,7 @@ def process_image(image):
 
     # Extract content from boxes
     extracted_content = {}
-    for idx, box in enumerate(encoding.bbox.tolist()):
+    for idx, box in enumerate(bbox):
         predicted_label = id2label[predicted_labels[idx]]
         box_width = np.array(box)[2] - np.array(box)[0]
         box_height = np.array(box)[3] - np.array(box)[1]
@@ -75,7 +75,7 @@ def process_image(image):
     # Draw predictions over the image
     draw = ImageDraw.Draw(image)
     font = ImageFont.load_default()
-    for prediction, box in zip(predicted_labels, encoding.bbox.tolist()):
+    for prediction, box in zip(predicted_labels, bbox):
         predicted_label = iob_to_label(id2label[prediction])
         box_width = np.array(box)[2] - np.array(box)[0]
         box_height = np.array(box)[3] - np.array(box)[1]