Deep GrabCut (DeepGC)
This is a PyTorch implementation of Deep GrabCut, for object segmentation. We use DeepLab-v2 instead of DeconvNet in this repository.
The code was tested with Python 3.5. To use this code, please do:
Clone the repo:
git clone https://github.com/jfzhang95/DeepGrabCut-PyTorch cd DeepGrabCut-PyTorch
pip install pytorch torchvision -c pytorch pip install matplotlib opencv pillow
You can download pretrained model from GoogleDrive, and then put the model into models/
To try the demo of Deep GrabCut, please run:
If installed correctly, the result should look like this:
To train Deep GrabCut on VOC (or VOC + SBD), please follow these additional steps:
Download the pre-trained PSPNet model for semantic segmentation, taken from this repository.
cd models/ chmod +x download_pretrained_psp_model.sh ./download_pretrained_psp_model.sh cd ..
Set the paths in
mypath.py, so that they point to the location of VOC/SBD dataset.
python train.pyto train Deep Grabcut.
If you want to train model on COCO dataset, you should first config COCO dataset path in mypath.py, and then run
python train_coco.pyto train model.