Hi, thanks for your sharing code, it's awesome work.
I'm a green hand in contrastive learning, I'm running your code with an NVIDIA Tesla T4, but it seems slowly for training and the GPU-Util can not always keep a value that is greater than 50%, is it a normal phenomenon?
It seems that the process of selecting queries and corresponding negative keys is time consuming.
Yes, since ReCo samples hard pixels and accumulates losses across all semantic classes, this is a common observation. You may speed up training by sampling a lower number of queries.
Hi, thanks for your sharing code, it's awesome work.
I'm a green hand in contrastive learning, I'm running your code with an NVIDIA Tesla T4, but it seems slowly for training and the GPU-Util can not always keep a value that is greater than 50%, is it a normal phenomenon?
It seems that the process of selecting queries and corresponding negative keys is time consuming.