Open qilong-zhang opened 3 years ago
Maybe the batch_size
is 16*4 = 64. I run the code with batch_size=4*4
, and the accuracy on the CUB_200_2011 dataset is only 90.9\%. After changing the batch_size
to 4*8 (limited by memory, 4*16 cause OOM on my server with 4 RTX3090 GPUs), the accuracy raises up to 91.4\%.
Hi @TACJu, I notice you apply DDP with 4 GPUs in
train.py
. Therefore, if the batch_size in args is set to 16, then the overall batch_size will be 16x4=64. However, in your paper, you say that the batch_size is 16. I also try batch_size 16x4 on Tesla V100, but OOM will be raised, so I wonderbatch_size is 16
means 16 or 64? thanks!