Spaces:
Runtime error
Runtime error
File size: 4,232 Bytes
e47538b a434c81 e47538b 4c5b48d 4dfb513 e47538b 747c9ad e47538b 747c9ad 1796d49 747c9ad f627d24 4f82f81 4dfb513 27d81b4 4dfb513 1e988ab 4dfb513 4f82f81 791261d 4dfb513 a434c81 e47538b a434c81 4c5b48d 0226999 6a34e60 e47538b cf6b359 e47538b 347d930 e47538b fe1f44f c5a6d21 fe1f44f c5a6d21 fe1f44f c5a6d21 fe1f44f c5a6d21 e47538b 1e988ab 250e824 b2a4c2e 747c9ad 347d930 5ff27bf 56cdfa2 e47538b 174240c e47538b 154403f 5ff27bf e47538b b0e9721 e47538b |
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 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 |
import pandas as pd
import PIL
from PIL import Image
from PIL import ImageDraw
import gradio as gr
import torch
import easyocr
import omegaconf
import cv2
import json
from vietocr.vietocr.tool.predictor import Predictor
from vietocr.vietocr.tool.config import Cfg
# Configure of VietOCR
config = Cfg.load_config_from_name('vgg_transformer')
# config = Cfg.load_config_from_file('vietocr/config.yml')
# config['weights'] = '/Users/bmd1905/Desktop/pretrain_ocr/vi00_vi01_transformer.pth'
config['cnn']['pretrained'] = True
config['predictor']['beamsearch'] = True
config['device'] = 'cpu' # mps
recognitor = Predictor(config)
#model_name = "microsoft/xdoc-base-squad2.0"
#nlp = pipeline('question-answering', model=model_name)
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "timpal0l/mdeberta-v3-base-squad2"
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
nlp = pipeline('question-answering', model=model, tokenizer=tokenizer)
def query(doc, labels):
questions = labels.split(", ")
result={}
for question in questions:
QA_input = {
'question': question+'?',
'context': doc
}
res= nlp(QA_input)
print(res)
value = res['answer']
result[question]=value
return result
def draw_boxes(image, bounds, color='yellow', width=2):
draw = ImageDraw.Draw(image)
for bound in bounds:
p0, p1, p2, p3 = bound[0]
draw.line([*p0, *p1, *p2, *p3, *p0], fill=color, width=width)
return image
def inference(filepath, lang, labels):
img = cv2.imread(filepath)
width, height, _ = img.shape
if width>height:
height, width, _ = img.shape
reader = easyocr.Reader(lang)
bounds = reader.readtext(filepath)
new_bounds=[]
texts=''
for (bbox, text, prob) in bounds:
(tl, tr, br, bl) = bbox
tl = (int(tl[0]), int(tl[1]))
tr = (int(tr[0]), int(tr[1]))
br = (int(br[0]), int(br[1]))
bl = (int(bl[0]), int(bl[1]))
min_x = min(tl[0], tr[0], br[0], bl[0])
min_x = max(0, min_x)
max_x = max(tl[0], tr[0], br[0], bl[0])
max_x = min(width-1, max_x)
min_y = min(tl[1], tr[1], br[1], bl[1])
min_y = max(0, min_y)
max_y = max(tl[1], tr[1], br[1], bl[1])
max_y = min(height-1, max_y)
# crop the region of interest (ROI)
cropped_image = img[min_y:max_y,min_x:max_x] # crop the image
cropped_image = Image.fromarray(cropped_image)
out = recognitor.predict(cropped_image)
texts = texts + '\t' + out
result = query(texts, labels)
jsonText = json.dumps(result)
im = PIL.Image.open(filepath)
draw_boxes(im, bounds)
im.save('result.jpg')
return ['result.jpg', texts, jsonText]
title = 'EasyOCR'
description = 'Gradio demo for EasyOCR. EasyOCR demo supports 80+ languages.To use it, simply upload your image and choose a language from the dropdown menu, or click one of the examples to load them. Read more at the links below.'
article = "<p style='text-align: center'><a href='https://www.jaided.ai/easyocr/'>Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.</a> | <a href='https://github.com/JaidedAI/EasyOCR'>Github Repo</a></p>"
css = ".output_image, .input_image {height: 40rem !important; width: 100% !important;}"
choices = [
"vi"
]
gr.Interface(
inference,
[gr.inputs.Image(type='filepath', label='Input'),gr.inputs.CheckboxGroup(choices, type="value", default=['vi'], label='language'), gr.inputs.Textbox(label='Labels',default='NgΖ°α»i nα»p, TiαΊΏp nhαΊn hα» sΖ‘ của')],
[gr.outputs.Image(type='pil', label='Output'), gr.outputs.Textbox(label='Text'), gr.outputs.JSON(label='document')],
title=title,
description=description,
article=article,
css=css,
examples=[['giaytiepnhan.jpg',['vi'],'NgΖ°α»i nα»p, TiαΊΏp nhαΊn hα» sΖ‘ của'],['giaytiepnhan2.jpg',['vi'],'MΓ£ sα» hα» sΖ‘, Δα»a chα»']],
enable_queue=True
).launch(debug=True) |