Update app.py

app.py

@@ -1,44 +1,56 @@
-"""
-Donut
-Copyright (c) 2022-present NAVER Corp.
-MIT License
-https://github.com/clovaai/donut
-"""
+import re
 import gradio as gr
+
 import torch
-from PIL import Image
 from transformers import DonutProcessor, VisionEncoderDecoderModel
 
-from donut import DonutModel
-
-def demo_process(input_img):
-    global pretrained_model, task_prompt, task_name
-    # input_img = Image.fromarray(input_img)
-    output = pretrained_model.inference(image=input_img, prompt=task_prompt)["predictions"][0]
-    return output
-
-task_prompt = f"<s_cord-v2>"
-
-
-#pretrained_model = DonutModel.from_pretrained("to-be/ID_cards_v1",revision="main")
-pretrained_model = VisionEncoderDecoderModel.from_pretrained("to-be/ID_cards_v1")
-pretrained_model.eval()
-
-
+processor = DonutProcessor.from_pretrained("to-be/ID_cards_v1")
+model = VisionEncoderDecoderModel.from_pretrained("to-be/ID_cards_v1")
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model.to(device)
+
+def process_document(image):
+    # prepare encoder inputs
+    pixel_values = processor(image, return_tensors="pt").pixel_values
+    
+    # prepare decoder inputs
+    task_prompt = "<s_cord-v2>"
+    decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids
+          
+    # generate answer
+    outputs = model.generate(
+        pixel_values.to(device),
+        decoder_input_ids=decoder_input_ids.to(device),
+        max_length=model.decoder.config.max_position_embeddings,
+        early_stopping=True,
+        pad_token_id=processor.tokenizer.pad_token_id,
+        eos_token_id=processor.tokenizer.eos_token_id,
+        use_cache=True,
+        num_beams=1,
+        bad_words_ids=[[processor.tokenizer.unk_token_id]],
+        return_dict_in_generate=True,
+    )
+    
+    # postprocess
+    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
+    
+    return processor.token2json(sequence)
+
+description = "Gradio Demo for Donut, an instance of `VisionEncoderDecoderModel` fine-tuned on CORD (document parsing). To use it, simply upload your image and click 'submit', or click one of the examples to load them. Read more at the links below."
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2111.15664' target='_blank'>Donut: OCR-free Document Understanding Transformer</a> | <a href='https://github.com/clovaai/donut' target='_blank'>Github Repo</a></p>"
 
 demo = gr.Interface(
-    fn=demo_process,
-    inputs= gr.inputs.Image(type="pil"),
+    fn=process_document,
+    inputs="image",
     outputs="json",
-    title=f"Donut 🍩 demonstration for `cord-v2` task",
-    description="""This model is trained with 800 Indonesian receipt images of CORD dataset. <br>
-Demonstrations for other types of documents/tasks are available at https://github.com/clovaai/donut <br>
-More CORD receipt images are available at https://huggingface.co/datasets/naver-clova-ix/cord-v2
-More details are available at:
-- Paper: https://arxiv.org/abs/2111.15664
-- GitHub: https://github.com/clovaai/donut""",
-    examples=[["3001.jpg"]],
-    cache_examples=False,
-)
+    title="Demo: Donut 🍩 for Document Parsing",
+    description=description,
+    article=article,
+    enable_queue=True,
+    examples=[["3001.png"]],
+    cache_examples=False)
 
 demo.launch()