- Python 3
- Pytorch 0.3.6
- torchvision
- visdom (optional for visualization)
The code was tested with Anaconda and Python 3.6. After installing the Anaconda environment:
-
Clone the repo:
git clone https://github.com/kh22l22/Auto-DEXTR-Pytorch cd Auto-DEXTR-Pytorch
-
Install dependencies:
conda install pytorch torchvision -c pytorch conda install matplotlib opencv pillow scikit-learn scikit-image
-
Run demo code
python demo.py
-
default choose: download and copy the pretrained model to
weights
directory.
NLFD: Luo Z, Mishra A, Achkar A, Eichel J, Li S-Z, Jodoin P-M, “Non-Local Deep Features for Salient Object Detection”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)
Deep Extreme Cut: K.K. Maninis*, S. Caelles*, J. Pont-Tuset, and L. Van Gool Deep Extreme Cut: From Extreme Points to Object Segmentation, Computer Vision and Pattern Recognition (CVPR), 2018.
Code borrows from NLFD and Deep Extreme Cut.