ICCV2019_MirrorNet
ICCV2019_MirrorNet copied to clipboard
Mhaiyang
Code for the ICCV 2019 paper "Where Is My Mirror?"
What is the threshold of your method ? I set threshold to 0.5 using your trained model the results is much smaller than your paper.
Hi, I am trying your code, your works are really good and unique. But is it possible that we have some contrast threshold or accuracy threshold or something? I tried...
Hi, thank you very much for proposing this interesting work. Could you share your training code of MirrorNet? Except the feature extractor, do you pre-train your MirrorNet on other dataset?...
In the contrast block, why use a shared BN layer instead of using a separate BN layer for each ccl feature? https://github.com/Mhaiyang/ICCV2019_MirrorNet/blob/032bc60dbd257a35871d68773ceaef9cfd445e05/mirrornet.py#L187 https://github.com/Mhaiyang/ICCV2019_MirrorNet/blob/032bc60dbd257a35871d68773ceaef9cfd445e05/mirrornet.py#L196 https://github.com/Mhaiyang/ICCV2019_MirrorNet/blob/032bc60dbd257a35871d68773ceaef9cfd445e05/mirrornet.py#L202 https://github.com/Mhaiyang/ICCV2019_MirrorNet/blob/032bc60dbd257a35871d68773ceaef9cfd445e05/mirrornet.py#L208 https://github.com/Mhaiyang/ICCV2019_MirrorNet/blob/032bc60dbd257a35871d68773ceaef9cfd445e05/mirrornet.py#L214
I have made suitable changes: 1. Instructions on Readme, like Python less than 3.7 is required and torch-vision less 1.0.0 is unavailable. 2. I have made changes to requirements.txt regarding...
