Curious about where is the ResNet looking at? This repo visualizes the class specific saliency map or discriminative location. It is MatConvNet re-implementation of Learning Deep Features for Discriminative Localization, Bolei Zhou et. al., without modifying the network or re-training. (Torch re-implementation can be found at this repo.) We look directly through the ResNet to see the world.
- The code relies on vlfeat, and matconvnet, which should be downloaded and built before running the experiments. You can use the following commend to download them.
git clone --recurse-submodules https://github.com/zhanghang1989/visualResNet.git
If you have problem with compiling, please refer to the link.
- Run the progrem form Matlab:
- Visualize Multiple Images:
visual('data', 'path/to/your/files', 'num', 30)