Vedastr is an open source scene text recognition toolbox based on PyTorch. It is designed to be flexible in order to support rapid implementation and evaluation for scene text recognition task.
-
Modular design
We decompose the scene text recognition framework into different components and one can easily construct a customized scene text recognition framework by combining different modules. -
Flexibility
Vedastr is flexible enough to be able to easily change the components within a module. -
Module expansibility
It is easy to integrate a new module into the vedastr project. -
Support of multiple frameworks
The toolbox supports several popular scene text recognition framework, e.g., CRNN, TPS-ResNet-BiLSTM-Attention, etc. -
Good performance
We re-implement the best model in deep-text-recognition-benchmark and get better average accuracy. What's more, we implement a simple baseline(ResNet-FC) and the performance is acceptable.
This project is released under Apache 2.0 license.
Note:
- We test our model on IIIT5K_3000, SVT, IC03_867, IC13_1015, IC15_2077,SVTP, CUTE80. The training data we used is MJSynth(MJ) and SynthText(ST). You can find the datasets below.
MODEL | CASE SENSITIVE | IIIT5k_3000 | SVT | IC03_867 | IC13_1015 | IC15_2077 | SVTP | CUTE80 | AVERAGE |
---|---|---|---|---|---|---|---|---|---|
TPS-ResNet-BiLSTM-Attention | False | 87.33 | 87.79 | 95.04 | 92.61 | 74.45 | 81.09 | 74.91 | 84.95 |
ResNet-FC | False | 85.03 | 86.4 | 94 | 91.03 | 70.29 | 77.67 | 71.43 | 82.38 |
AVERAGE : Average accuracy over all test datasets
TPS : Spatial transformer network
CASE SENSITIVE : If true, the output is case sensitive and contain common characters.
If false, the output is not case sentive and contains only numbers and letters.
- Linux
- Python 3.6+
- PyTorch 1.1.0 or higher
- CUDA 9.0 or higher
We have tested the following versions of OS and softwares:
- OS: Ubuntu 16.04.6 LTS
- CUDA: 9.0
- Python 3.6.9
a. Create a conda virtual environment and activate it.
conda create -n vedastr python=3.6 -y
conda activate vedastr
b. Install PyTorch and torchvision following the official instructions, e.g.,
conda install pytorch torchvision -c pytorch
c. Clone the vedastr repository.
git clone https://github.com/Media-Smart/vedastr.git
cd vedastr
vedastr_root=${PWD}
d. Install dependencies.
pip install -r requirements.txt
a. Download Lmdb data from deep-text-recognition-benchmark, which contains training data, validation data and evaluation data.
b. Make directory data as follows:
cd ${vedastr_root}
mkdir ${vedastr_root}/data
c. Put the download Lmdb data into this data directory, the structure of data directory will look like as follows:
data
└── data_lmdb_release
├── evaluation
├── training
│ ├── MJ
│ │ ├── MJ_test
│ │ ├── MJ_train
│ │ └── MJ_valid
│ └── ST
└── validation
a. Config
Modify some configuration accordingly in the config file like configs/clova.py
b. Run
python tools/trainval.py configs/clova.py
Snapshots and logs will be generated at vedastr/workdir
.
a. Config
Modify some configuration accordingly in the config file like configs/clova.py
b. Run
python tools/test.py configs/clova.py path_to_clova_weights
This repository is currently maintained by Jun Sun(@ChaseMonsterAway), Hongxiang Cai (@hxcai), Yichao Xiong (@mileistone).
We got a lot of code from mmcv , mmdetection, deep-text-recognition-benchmark and vedaseg thanks to open-mmlab, clovaai, Media-Smart.