Spaces:
Running
Running
| import re | |
| from transformers import DonutProcessor, VisionEncoderDecoderModel | |
| from datasets import load_dataset | |
| import torch | |
| import streamlit as st | |
| from PIL import Image | |
| import PyPDF2 | |
| from pypdf.errors import PdfReadError | |
| from pypdf import PdfReader | |
| import pypdfium2 as pdfium | |
| document = st.file_uploader(label="Upload the document you want to explore",type=["png",'jpg', "jpeg","pdf"]) | |
| model_option = st.selectbox("Select the output of the model:",["Classification","Extract Info"]) | |
| if model_option == "Classification": | |
| processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-rvlcdip") | |
| model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-rvlcdip") | |
| device = "cpu" | |
| model.to(device) | |
| # load document image | |
| if document == None: | |
| st.write("Please upload the document in the box above") | |
| else: | |
| try: | |
| PdfReader(document) | |
| pdf = pdfium.PdfDocument(document) | |
| page = pdf.get_page(0) | |
| pil_image = page.render(scale = 300/72).to_pil() | |
| task_prompt = "<s_rvlcdip>" | |
| decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids | |
| pixel_values = processor(pil_image, return_tensors="pt").pixel_values | |
| outputs = model.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 | |
| st.image(pil_image,"Document uploaded") | |
| st.write(processor.token2json(sequence)) | |
| except PdfReadError: | |
| document = Image.open(document) | |
| task_prompt = "<s_rvlcdip>" | |
| decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids | |
| pixel_values = processor(document, return_tensors="pt").pixel_values | |
| outputs = model.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 | |
| st.image(document,"Document uploaded") | |
| st.write(processor.token2json(sequence)) | |
| elif model_option == "Extract Info": | |
| processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2") | |
| model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2") | |
| device = "cpu" | |
| model.to(device) | |
| # load document image | |
| if document == None: | |
| st.write("Please upload the document in the box above") | |
| else: | |
| try: | |
| PdfReader(document) | |
| pdf = pdfium.PdfDocument(document) | |
| page = pdf.get_page(0) | |
| pil_image = page.render(scale = 300/72).to_pil() | |
| task_prompt = "<s_cord-v2>" | |
| decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids | |
| pixel_values = processor(pil_image, return_tensors="pt").pixel_values | |
| outputs = model.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 | |
| st.image(pil_image,"Document uploaded") | |
| st.write(processor.token2json(sequence)) | |
| except PdfReadError: | |
| document = Image.open(document) | |
| task_prompt = "<s_cord-v2>" | |
| decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids | |
| pixel_values = processor(document, return_tensors="pt").pixel_values | |
| outputs = model.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 | |
| st.image(document,"Document uploaded") | |
| st.write(processor.token2json(sequence)) |