File size: 1,600 Bytes
8c52817 e24f049 8c52817 e24f049 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 |
import re
from transformers import DonutProcessor, VisionEncoderDecoderModel
from datasets import load_dataset
import torch
from PIL import Image
import numpy as np
import streamlit as st
processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-rvlcdip")
model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-rvlcdip")
device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)
#image = Image.open(r"C:\Invoices\Sample Invoices\sample invoice 1.tif")
#image = image.convert("RGB")
#print(np.array(image).shape)
# load document image
dataset = load_dataset("hf-internal-testing/example-documents", split="test")
image = dataset[2]["image"]
task_prompt = "<s_rvlcdip>"
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.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
print(processor.token2json(sequence))
|