small batchsize has a lower mAP.

[DL-ljw]

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.

[szq0214]

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

[DL-ljw]

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

[DL-ljw]

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.