https://github.com/meijieru/crnn.pytorch

Convolutional recurrent network in pytorch
https://github.com/meijieru/crnn.pytorch

neural-network recognition scene-texts

Last synced: about 12 hours ago
JSON representation

Convolutional recurrent network in pytorch

• Host: GitHub
• URL: https://github.com/meijieru/crnn.pytorch
• Owner: meijieru
• License: mit
• Created: 2017-02-27T09:26:06.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2024-09-19T06:50:05.000Z (8 months ago)
• Last Synced: 2025-04-11T14:16:51.936Z (about 1 month ago)
• Topics: neural-network, recognition, scene-texts
• Language: Python
• Size: 37.1 KB
• Stars: 2,438
• Watchers: 53
• Forks: 656
• Open Issues: 103
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
Convolutional Recurrent Neural Network

======================================

This software implements the Convolutional Recurrent Neural Network (CRNN) in pytorch.

Origin software could be found in [crnn](https://github.com/bgshih/crnn)

Run demo

--------

A demo program can be found in ``demo.py``. Before running the demo, download a pretrained model

from [Baidu Netdisk](https://pan.baidu.com/s/1pLbeCND) or [Dropbox](https://www.dropbox.com/s/dboqjk20qjkpta3/crnn.pth?dl=0). 

This pretrained model is converted from auther offered one by ``tool``.

Put the downloaded model file ``crnn.pth`` into directory ``data/``. Then launch the demo by:

    python demo.py

The demo reads an example image and recognizes its text content.

Example image:

![Example Image](./data/demo.png)

Expected output:

    loading pretrained model from ./data/crnn.pth

    a-----v--a-i-l-a-bb-l-ee-- => available

Dependence

----------

* [warp_ctc_pytorch](https://github.com/SeanNaren/warp-ctc/tree/pytorch_bindings/pytorch_binding)

* lmdb

Train a new model

-----------------

1. Construct dataset following [origin guide](https://github.com/bgshih/crnn#train-a-new-model). If you want to train with variable length images (keep the origin ratio for example), please modify the `tool/create_dataset.py` and sort the image according to the text length.

2. Execute ``python train.py --adadelta --trainRoot {train_path} --valRoot {val_path} --cuda``. Explore ``train.py`` for details.

Cite

----

```tex

@article{shi2016end,

  title={An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition},

  author={Shi, Baoguang and Bai, Xiang and Yao, Cong},

  journal={IEEE transactions on pattern analysis and machine intelligence},

  volume={39},

  number={11},

  pages={2298--2304},

  year={2016},

  publisher={IEEE}

}

```