MMOCR / app.py
tomofi's picture
Add application file
2366e36
raw
history blame
No virus
2.05 kB
import os
import torch
print(torch.__version__)
torch_ver, cuda_ver = torch.__version__.split('+')
os.system(f'pip install mmdet mmcv-full -f https://download.openmmlab.com/mmcv/dist/{cuda_ver}/torch{torch_ver}/index.html --no-cache-dir')
os.system('wget -c https://download.openmmlab.com/mmocr/data/wildreceipt.tar; mkdir -p data; tar -xf wildreceipt.tar --directory data; rm -f wildreceipt.tar')
import datetime
import gradio as gr
import pandas as pd
from mmocr.utils.ocr import MMOCR
def inference(img):
print(datetime.datetime.now(), 'start')
ocr = MMOCR(det='PS_CTW', recog='SAR', kie='SDMGR')
print(datetime.datetime.now(), 'start read')
results = ocr.readtext(img.name, details=True, output='result.png')
print(datetime.datetime.now(), results)
return ['result.png', pd.DataFrame(results[0]['result']).iloc[: , 2:]]
description = 'Gradio demo for MMOCR. MMOCR is an open-source toolbox based on PyTorch and mmdetection for text detection, text recognition, and the corresponding downstream tasks including key information extraction. To use it, simply upload your image or click one of the examples to load them. Read more at the links below.'
article = "<p style='text-align: center'><a href='https://mmocr.readthedocs.io/en/latest/'>MMOCR is an open-source toolbox based on PyTorch and mmdetection for text detection, text recognition, and the corresponding downstream tasks including key information extraction.</a> | <a href='https://github.com/open-mmlab/mmocr'>Github Repo</a></p>"
gr.Interface(inference,
gr.inputs.Image(type='file', label='Input'),
[gr.outputs.Image(type='file', label='Output'), gr.outputs.Dataframe(headers=['text', 'text_score', 'label', 'label_score'])],
title='MMOCR',
description=description,
article=article,
examples=['demo/demo_kie.jpeg', 'demo/demo_text_ocr.jpg', 'demo/demo_text_det.jpg', 'demo/demo_densetext_det.jpg'],
css=".output_image, .input_image {height: 40rem !important; width: 100% !important;}",
enable_queue=True
).launch(debug=True)