Pytorch implement of Deeply Supervised Salient Object Detection with Short Connection

The official caffe version: DSS

• Python 3
• Pytorch 0.3.0
• torchvision
• visdom (optional for visualization)

The information of Loss:

Example output:

git clone [email protected]:AceCoooool/DSS-pytorch.git
cd DSS-pytorch/

Note: the original paper use other datasets.

Download the ECSSD dataset. (see NLFD-pytorch)

bash download.sh

cd tools/
python extract_vgg.py
cd ..

python demo.py --demo_img='your_picture' --trained_model='pre_trained pth' --cuda=True

Note:

1. default choose: download and copy the pretrained model to weights directory
2. a demo picture is in png/demo.jpg

python main.py --mode='train' --train_path='you_data' --label_path='you_label' --batch_size=8 --visdom=True

Note:

1. --val=True add the validation (but your need to add the --val_path and --val_label)
2. you_data, you_label means your training data root. (connect to the step 2)

python main.py --mode='test', --test_path='you_data' --test_label='your_label' --batch_size=1 --model='your_trained_model'

• add RCF process
• test other connection situation