memory increased with steps

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

memory increased with steps #6

Closed BrandonHanx closed 3 years ago

BrandonHanx commented 3 years ago

Hi all, @X-ing @girafffeee

I found the memory increased with steps (about 20MB for several ten steps). This is not a good thing. Did you encounter the same phenomenon?'

BTW, would you please take a little time to clean this repo? The code is a little bit messy (too many unused variables and imports, no lint and so on)...

Thanks

BrandonHanx commented 3 years ago

What's more, would you please release the trained model? Because your random seed seems like non-fixed ...

wettera commented 3 years ago

What's more, would you please release the trained model? Because your random seed seems like non-fixed ...

Thanks for your attention on our work. I have uploaded the trained model and the training log.