Update app.py

app.py

@@ -23,7 +23,7 @@ st.title("Classify Document Image")
 file_name = st.file_uploader("Upload a candidate image")
 
 if file_name is not None:
-    col1, col2 = st.columns(2)
+    col1, col2, col3 = st.columns(3)
 
     image = Image.open(file_name)
     image = image.convert("RGB")
@@ -58,7 +58,32 @@ if file_name is not None:
 
     col2.header("Results")
     col2.subheader(processor.token2json(sequence))
-   
+    
+    processor_ext = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
+    model_ext = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
 
+    model_ext.to(device)
+   
+    # prepare decoder inputs
+    task_prompt = "<s_cord-v2>"
+    decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids
+    
+    pixel_values = processor(image, return_tensors="pt").pixel_values
 
+    outputs = model_ext.generate(
+        pixel_values.to(device),
+        decoder_input_ids=decoder_input_ids.to(device),
+        max_length=model.decoder.config.max_position_embeddings,
+        pad_token_id=processor.tokenizer.pad_token_id,
+        eos_token_id=processor.tokenizer.eos_token_id,
+        use_cache=True,
+        bad_words_ids=[[processor.tokenizer.unk_token_id]],
+        return_dict_in_generate=True,
+    )
 
+    sequence = processor.batch_decode(outputs.sequences)[0]
+    sequence = sequence.replace(processor.tokenizer.eos_token, "").replace(processor.tokenizer.pad_token, "")
+    sequence = re.sub(r"<.*?>", "", sequence, count=1).strip()  # remove first task start token
+    col3.header("Features")
+    col3.subheader(processor.token2json(sequence))
+