51 lines
2.1 KiB
Python
51 lines
2.1 KiB
Python
from transformers import DonutProcessor, VisionEncoderDecoderModel
|
|
import gradio as gr
|
|
from PIL import Image
|
|
import torch
|
|
import re
|
|
|
|
|
|
processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa")
|
|
model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa")
|
|
|
|
|
|
def vqa(image, question):
|
|
inp = Image.fromarray(image.astype('uint8'), 'RGB')
|
|
pixel_values = processor(inp, return_tensors="pt").pixel_values
|
|
task_prompt = "{user_input}"
|
|
prompt = task_prompt.replace("{user_input}", question)
|
|
decoder_input_ids = processor.tokenizer(prompt, add_special_tokens=False, return_tensors="pt")["input_ids"]
|
|
|
|
device = "cuda" if torch.cuda.is_available() else "cpu"
|
|
model.to(device)
|
|
|
|
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,
|
|
output_scores=True)
|
|
|
|
|
|
seq = processor.batch_decode(outputs.sequences)[0]
|
|
seq = seq.replace(processor.tokenizer.eos_token, "").replace(processor.tokenizer.pad_token, "")
|
|
seq = re.sub(r"<.*?>", "", seq, count=1).strip()
|
|
|
|
return processor.token2json(seq)
|
|
|
|
|
|
demo = gr.Interface(fn=vqa,
|
|
inputs=['image', 'text'],
|
|
outputs='text',
|
|
title = "vqa",
|
|
examples = [['income.png', 'What are the 2020 net sales?'], ['invoice.png','What is the invoice number?']])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
demo.queue(concurrency_count=3).launch(server_name = "0.0.0.0", server_port = 7026)
|