Real-time Scene Text Detection with Differentiable Binarization

note: some code is inherited from MhLiao/DB

中文解读

Install

conda create --name DBNet.pytorch -y
conda activate DBNet.pytorch

conda install ipython pip

# python dependencies
pip install -r requirement.txt

# install PyTorch with cuda-10.1
conda install pytorch torchvision cudatoolkit=10.1 -c pytorch

# clone repo
git clone https://github.com/WenmuZhou/DBNet.pytorch.git
cd DBNet.pytorch/

# build deformable convolution opertor
cd models/modules/dcn
python setup.py build_ext --inplace

Requirements

• pytorch 1.1+
• torchvision 0.3+
• gcc 4.9+

Download

TBD

Data Preparation

train: prepare a text in the following format, use '\t' as a separator

/path/to/img.jpg path/to/label.txt
...

val: use a folder

img/ store img
gt/ store gt file

Train

1. config the dataset['train']['dataset'['data_path']',dataset['validate']['dataset'['data_path']in config/icdar2015_resnet18_fpn_DBhead_polyLR.yaml
2. single gpu train

bash singlel_gpu_train.sh

3. Multi-gpu training

bash multi_gpu_train.sh

Test

eval.py is used to test model on test dataset

1. config model_path in eval.sh
2. use following script to test

bash eval.sh

Predict

predict.py is used to inference on single image

1. config model_path, img_path, in predict.py
2. use following script to predict

python3 predict.py

The project is still under development.

Performance

ICDAR 2015

only train on ICDAR2015 dataset

Method	image size (short size)	learning rate	Precision (%)	Recall (%)	F-measure (%)	FPS
DB-ResNet-18(paper)	736	0.007	86.8	78.4	82.3	48
TBD	736	1e-3	TBD	TBD	TBD	TBD

examples

TBD

todo

• mutil gpu training

reference

1. https://arxiv.org/pdf/1911.08947.pdf
2. https://github.com/WenmuZhou/PANet.pytorch
3. https://github.com/MhLiao/DB

If this repository helps you，please star it. Thanks.