search

backseason / PoolNet

Code for our CVPR 2019 paper "A Simple Pooling-Based Design for Real-Time Salient Object Detection"
MIT License
629 stars 153 forks source link

about test #2

Closed KaaiLee closed 5 years ago

KaaiLee commented 5 years ago

hi,thanks for your project.Ｉs it only possible to test with public datasets in your project? If I want to test with my own dataset, what should I do?

backseason commented 5 years ago
  1. Prepare your images under one folder X and generate the corresponding .lst file Y.
  2. Set the 'image_root' and 'image_source' params in the 'main.py' file to X and Y.
  3. At test time set the '--sal_mode' param to your image settings.