A research project for text detection and recognition using PyTorch 1.2.
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.
pip install -r requirements.txt
cd PATH_TO_OPS
python setup.py build_ext --inplace
ops may be used:
assets/ops/dcn
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. Also, lmdb format data are now available too. You can refer the usage in demo. Datasets used in our recognition experiments can be downloaded from onedrive. The transform script are provide to convert json format data to lmdb.
python3 train.py PATH_TO_EXPERIMENT.yaml --validate --visualize --name NAME_OF_EXPERIMENT
Following we provide some of configurations of the released recognition models:
experiments/recognition/crnn.yaml
experiments/recognition/res50-ppm-2d-ctc.yaml
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.