search

chenhao2345 / ICE

Implementation for ICCV 2021 paper "ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification"
MIT License
44 stars 15 forks source link

Performance degrades #8

Closed YangJae96 closed 2 years ago

YangJae96 commented 2 years ago

Why does the performance degrade when I use only 1 GPU with all the same hyper-parameter?

How should I change the parameters when using 1 GPU.

chenhao2345 commented 2 years ago

The gpu number, batchsize and learning rate can always affect results, because we use DataParellel mode.

I used 4 GPUs to train. Thus, the batchsize and learning rate values in our paper are tuned based on 4 GPUs.

If you have enough GPUs, try to use 4 GPUs. Otherwise, you may need to search optimal batchsize and learning rate values to find best results. Wish this can help you.