| import os | |
| os.system('pip install --upgrade gdown') | |
| import gdown | |
| gdown.download(id='1mYM_26qHUom_5NU7iutHneB_KHlLjL5y', output='workdir.zip') | |
| os.system('unzip workdir.zip') | |
| import glob | |
| import gradio as gr | |
| from demo import get_model, preprocess, postprocess, load | |
| from utils import Config, Logger, CharsetMapper | |
| def process_image(image): | |
| config = Config('configs/train_abinet.yaml') | |
| config.model_vision_checkpoint = None | |
| model = get_model(config) | |
| model = load(model, 'workdir/train-abinet/best-train-abinet.pth') | |
| charset = CharsetMapper(filename=config.dataset_charset_path, max_length=config.dataset_max_length + 1) | |
| img = image.convert('RGB') | |
| img = preprocess(img, config.dataset_image_width, config.dataset_image_height) | |
| res = model(img) | |
| return postprocess(res, charset, 'alignment')[0][0] | |
| title = "Interactive demo: ABINet" | |
| description = "Demo for ABINet, ABINet uses a vision model and an explicit language model to recognize text in the wild, which are trained in end-to-end way. The language model (BCN) achieves bidirectional language representation in simulating cloze test, additionally utilizing iterative correction strategy. To use it, simply upload a (single-text line) image or use one of the example images below and click 'submit'. Results will show up in a few seconds." | |
| article = "<p style='text-align: center'><a href='https://arxiv.org/pdf/2103.06495.pdf'>Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition</a> | <a href='https://github.com/FangShancheng/ABINet'>Github Repo</a></p>" | |
| iface = gr.Interface(fn=process_image, | |
| inputs=gr.inputs.Image(type="pil"), | |
| outputs=gr.outputs.Textbox(), | |
| title=title, | |
| description=description, | |
| article=article, | |
| examples=glob.glob('figs/test/*.png')) | |
| iface.launch(debug=True) |