This is the code repository for the paper:
Cross-Domain Complementary Learning with Synthetic Data for Multi-Person Part Segmentation
Kevin Lin, Lijuan Wang, Kun Luo, Yinpeng Chen, Zicheng Liu, Ming-Ting Sun
[Paper] [Demo Video]
pip install -r requiremet.txt
is developed Python 3 CUDA 10.0, CUDNN 7.4.1.5, Tensorflow 1.10.0, Keras 2.2.4
Please download the pre-trained model using the following command:
cd CDCL_human-part
fetch_data.sh
We suggest creating a new conda environment for setting up the relevant dependencies. After installing Anaconda on your machine, please run the following command:
$ conda env create -f cdcl_environment.yaml
After creating the environment, you just need to activate the environment and continue running the demo code.
$ conda activate cdcl
python train.py --help
[Usage]
python cdlc_cam.py --gpus [N] --model [mmodel name] --output_folder[output file] --scale [SCALE]