search

SHI-Labs / Self-Similarity-Grouping

Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification (ICCV 2019, Oral)
187 stars 43 forks source link

Are you sure this code is running. There are a lot of miskates #18

Closed jpainam closed 5 years ago

jpainam commented 5 years ago

Hi; thank you for sharing But your code has a lot of mistake; I'm inclined to say; it can't execute. Except we modified them. Pls, make sure you upload a running code out of the box? For example; here; you used cross_entropy without self.cross_entropy. https://github.com/OasisYang/SSG/blob/b607ab650d2e01a984861a041b7cd248e727d621/reid/loss/weight_cross_entropy.py#L21

in reid/loss/triplet.py L35, the code is unreachable, you used if False

jpainam commented 5 years ago

Hi; I suggest you try to solve these issues instead of just closing them. We understand it's your code and we would like to get similar results. This line of code I highlighted doesn't even compile because you wrote cross_entropy instead of F.cross_entropy or self.cross_entropy

Thank you for solving the issue to make your code clean for the community