How did you warm up identity encoder?? about gcl HOT 3 OPEN

Our encoder has two branches after CNN layers: one branch outputs 2048x4x1 for generative part with part average pooling, the other one outputs 2048x1x1 for ReID training with normal average pooling. The second one is used for warm up.

We just run the source code (JVTC or MLC) and saved their weights as Stage 1. In stage 2, we load the saved weights into our ft_net.

from gcl.

Thank you.

One more question.
Do you have the code for getting the Fid and SSIM scores in your paper??

It will be great if you can provide this also for checking Generator's ability.

from gcl.

To get FID and SSIM, first generate images with our examples/generate_data.py. Then, use following project code

FID: https://github.com/layumi/TTUR
SSIM: https://github.com/layumi/PerceptualSimilarity

from gcl.