This is a project concerning Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild
we propose a synthetic-to-real domain adaptation method for scene text detection, which transfers knowledge from synthetic data (source domain) to real data (target domain)
From more details,please refer to our arXiv paper.(TDB)
- python 3
- torch = 1.1.0
- torchvision
- Pillow
- numpy
Our experiments are based on one machine with 2 2080ti(16g memory).
(TDB)
for example (batchsize=2)
CUDA_VISIBLE_DEVICES=0 python -u eval.py
For academic use, this project is licensed under the Apache License - see the LICENSE file for details. For commercial use, please contact the authors.
Please consider citing our paper in your publications if the project helps your research.
Eamil: weijia_wu@yeah.net