This is an implementation of Real-time Scene Text Detection with Differentiable Binarization in Keras and Tensorflow, Most portions of code are borrowed from the official implementation MhLiao/DB.
Build dataset in the same way as the official implementation.
datasets/total_text/train_images
datasets/total_text/train_gts
datasets/total_text/train_list.txt
datasets/total_text/test_images
datasets/total_text/test_gts
datasets/total_text/test_list.txt
The root of the dataset directory can be DB/datasets/.
Download the converted ground-truth and data list Baidu Drive (download code: mz0a), Google Drive. The images of each dataset can be obtained from their official website.
python train.py
You can download a trained model weights on TotalText by baidu netdisk code:jy6m or google driver
python inference.py