Awesome
SieveNet
This is the unofficial implementation of 'SieveNet: A Unified Framework for Robust Image-Based Virtual Try-On' </br> Paper can be found from here
Dataset downloading and processing
Dataset download instructions and link of dataset can be found from official repo of CP-VTON and VITON </br>
Put dataset in data
folder
Usage
Clone the repo and install requirements through pip install -r requirements.txt
Traning
Coarse-to-Fine Warping module
In config.py
set self.datamode='train'
and self.stage='GMM'
</br> then run python train.py
</br> You can observe results while traning in tensorboard as below
</br>
Conditional Segmentation Mask generation module
In config.py
set self.datamode='Train'
and self.stage='SEG'
</br> then run python train.py
</br>
Segmentation Assisted Texture Translation module
In config.py
set self.datamode='Train'
and self.stage='TOM'
</br> then run python train.py
</br>
Testing on dataset
Please download checkpoint of all three modules from google drive and put them in checkpoints
folder
</br>
For testing, in config.py
set self.datamode='test'
</br> For Testing of Coarse-to-Fine Warping module, Conditional Segmentation Mask generation module, and Segmentation Assisted Texture Translation module set self.stage='GMM'
, self.stage='SEG'
, and self.stage='TOM'
respectively.
</br>
Here is testing result. For Coarse-to-Fine Warping module,
</br>
</br>For Segmentation Assisted Texture Translation module,
</br>
Testing on custom image
- Please download checkpoint of all three modules from google drive and put them in
checkpoints
folder. - Please download caffe-model from here and put the model in
pose
folder. </br> - Generate human parsing from Self-Correction-Human-Parsing repo or from this colab demo. </br> Select
LIP
dataset while generating human parsing.</br> - Set input-image's, cloth-image's, and output of human parsing image's path in config file.</br>
- Then run
python inference.py
Output will be saved inoutputs
folder.
Update: Inference using colab
Please find inference code of Sievenet in 2nd part of this notebook
Acknowledgements
Some modules of this implementation is based on this repo</br> For generating pose keypoints, I have used learnopencv implementation of OpenPose