small batchsize has a lower mAP.

Question

small batchsize has a lower mAP.

Opened this issue 6 years ago · 3 comments

Hi, @szq0214:
I only have two GTX 1080 GPUs. I want to reproduce you GRP-DSOD. When I change the batch_size and accum_batch_size to 6 and 30, the mAP is just 63%. What I should do to get the results as you paper?
Thanks.

Answer 1 · 2018-03-06T07:07:06.000Z

@DL-ljw, batch_size can be a small value (6 is fine), but accum_batch_size should be 128 or larger.

Answer 2 · 2018-03-06T07:17:48.000Z

When accum_batch_size is 128, it wil train a very long time. Maybe I should have a better machine,

Answer 3 · 2018-03-22T23:57:04.000Z

Hi, @szq0214:
several days later.
I set batch_size = 6 and accum_batch_size = 128, it run 250 hours, and mAP is 76.5%(lower than 79.0 % in paper on pascal voc 2007 test)? Is the batch_size too small? What should I do next? We are planing to buy four GTX1080, these can set a larger batchsize, can they work?
Thanks.