A pytorch framework for building neurals networks for visual recognition, encoding, and detection tasks. The goal is to bridge the gap between research and production code, making AI/CV research code re-usable and reproducible
Thank you for the awesome code. I have trained the triplet detector for cars on kitti and I am able to get visualization of filter outputs. But unfortunately I am unable to run the tester.py. There is issue with mismatch in saved model state dict.
I was wondering if you can inform how to get inference of the correlation detector on an entire image (like the ones showed in homepage)?