CRAFT-Pyotorch：Character Region Awareness for Text Detection Reimplementation for Pytorch
Youngmin Baek, Bado Lee, Dongyoon Han, Sangdoo Yun, Hwalsuk Lee (Submitted on 3 Apr 2019)
The full paper is available at: https://arxiv.org/pdf/1904.01941.pdf
5、4 nvidia GPUs(we use 4 nvidia titanX)
NOTE: There are old pre-trained models, I will upload the new results pre-trained models' link.
Note: When you train the IC15-Data or MLT-Data, please see the annotation in data_loader.py line 92 and line 108-112.
(1、/data/CRAFT-pytorch/SynthText -> /your_path/SynthText 2、/data/CRAFT-pytorch/synweights/synweights -> /your_path/real_weights)
(1、/data/CRAFT-pytorch/SynthText -> /your_path/SynthText 2、/data/CRAFT-pytorch/real_weights -> /your_path/real_weights)
(1、/data/CRAFT-pytorch/1-7.pth -> /your_path/your_pre-trained_model_name 2、/data/CRAFT-pytorch/icdar1317 -> /your_ic15data_path/)
This code supprts for Syndata and icdar2015, and we will release the training code for IC13 and IC17 as soon as possible.
|Syndata+MLT(deteval)(new gaussian map method)||ICDAR13||90.67%||94.56%||92.57%
|Syndata+IC15(new gaussian map method)||ICDAR15||80.36%||84.25%||82.26%|
Note:new gaussian map method can split the inference gaussian region score map
Note:We have solved the problem about detecting big word. Now we are training the model. And any issues or advice are welcome.
We will release training code as soon as possible， and we have not yet reached the results given in the author's paper. Any pull requests or issues are welcome. We also hope that you could give us some advice for the project.
Thanks for Youngmin Baek, Bado Lee, Dongyoon Han, Sangdoo Yun, Hwalsuk Lee excellent work and code for test. In this repo, we use the author repo's basenet and test code.
For commercial use, please contact us.