search

TencentYoutuResearch / PersonReID-NAFS

Code for "Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search"
https://arxiv.org/abs/2101.03036
Other
61 stars 10 forks source link

Some confusion about the utilized jaccard distance in code #3

Closed ZJWang9928 closed 3 years ago

ZJWang9928 commented 3 years ago

Thanks for your code, but I have some confusion about the Jaccard distance API used in your testing code.

https://github.com/TencentYoutuResearch/PersonReID-NAFS/blob/5301b8d95bb711f88357d71cff1a9aaaac76f473/utils/metric.py#L482

As we can see in the document of SciPy, scipy.distance.jaccard is used to compute the Jaccard-Needham dissimilarity between two boolean 1-D arrays. It seems that it is not the expected implementation of the Jaccard Distance in your paper. Is it ok to directly use this API?

girafffeee commented 3 years ago

Thanks for your code, but I have some confusion about the Jaccard distance API used in your testing code.

https://github.com/TencentYoutuResearch/PersonReID-NAFS/blob/5301b8d95bb711f88357d71cff1a9aaaac76f473/utils/metric.py#L482

As we can see in the document of SciPy, scipy.distance.jaccard is used to compute the Jaccard-Needham dissimilarity between two boolean 1-D arrays. It seems that it is not the expected implementation of the Jaccard Distance in your paper. Is it ok to directly use this API?

Thank you very much. We fixed this bug here