A project for research in text detection and recognition using PyTorch 1.2.

This project is originated from the research repo, which heavily relies on closed-source libraries, of CSG-Algorithm team of Megvii(https://megvii.com). We are in ongoing progress to transfer models into this repo gradually, released implementations are listed in Progress.

• Implementations of representative text detection and recognition methods.
• An effective framework for conducting experiments: We use yaml files to configure experiments, making it convenient to take experiments.
• Thorough logging features which make it easy to follow and analyze experimental results.
• CPU/GPU compatible for training and inference.
• Distributed training support.

pip install -r requirements.txt

• Python3.7
• PyTorch 1.2 and CUDA 10.0.
• gcc 5.5(Important for compiling)

cd PATH_TO_OPS

python setup.py build_ext --inplace

ops may be used:

• DeformableConvV2 assets/ops/dcn
• CTC2DLoss ops/ctc_2d

Edit configurations in config.py.

See detailed options: python3 train.py --help

We provide data loading implementation with annotation packed with json for quick start. Datasets used in our recognition experiments can be downloaded from onedrive.

python3 train.py PATH_TO_EXPERIMENT.yaml --validate --visualize --name NAME_OF_EXPERIMENT

Following we provide some of configurations of the released recognition models:

• CRNN: experiments/recognition/crnn.yaml
• 2D CTC: experiments/recognition/res50-ppm-2d-ctc.yaml
• Attention Decoder: experiments/recognition/fpn50-attention-decoder.yaml

python3 -m torch.distributed.launch --nproc_per_node=NUM_GPUS train.py PATH_TO_EXPERIMENT.yaml -d --validate

See detailed options: python3 eval.py --help.

Keeping ratio tesing is recommended: python3 eval.py PATH_TO_EXPERIMENT.yaml --resize_mode keep_ratio

Trained models are comming soon.

• 2D CTC
• CRNN
• Attention Decoder
• Rectification

• Text Snake
• EAST

• Mask Text Spotter

Contributing.md