This is tensorflow implementation for cvpr2017 paper "Deeply Supervised Salient Object Detection with Short Connections"
https://drive.google.com/open?id=0B6l9O8aWij8fUGtVNldUTXA4eHc 1. Download pretrained model and put them under folder "salience_model" ,(need to create folder yourself)2. run code
If you want to test whole folder images, run this:
python inference.py --rgb_folder=[your folder]
sample:
python inference.py --rgb_folder=./test
If you want to test only one image,run this:
python inference.py --rgb=[your image]
sample:
python inference.py --rgb=animal1.jpg
more detail please read source code.
I'm considering to open source training code recently(in several months), but to be honest, I don't understand why this model works so well(even there is some mis-using of tensorflow, but it works..).