File size: 1,672 Bytes
a9a663b dfae955 c54a77d a9a663b c54a77d a9a663b 65e8bf8 |
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 49 50 |
import re
import transformers
from PIL import Image
from transformers import DonutProcessor, VisionEncoderDecoderModel
import torch
import random
import numpy as np
import gradio as gr
access_token = ""
transformers.logging.disable_default_handler()
processor = DonutProcessor.from_pretrained("daquarti/donut-base-sroie", use_auth_token=access_token)
model = VisionEncoderDecoderModel.from_pretrained("daquarti/donut-base-sroie", use_auth_token=access_token)
device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)
def load_image (f):
with Image.open(f) as img:
a = img.load()
return img.convert('RGB')
def pred (a):
#imagen_path = imagen
#a = load_image (imagen_path)
pixel_values = processor(a, return_tensors="pt").pixel_values
task_prompt = "<s>"
decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids
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,
)
prediction = processor.batch_decode(outputs.sequences)[0]
prediction = processor.token2json(prediction)
return str (prediction)
examples = ['1.jpg', '2.jpg']
demo = gr.Interface(fn=pred, inputs="image", outputs= "text", examples= examples)
demo.launch(share= False) |