questions about batch size in GHMC_loss

[longchuan1985]

Hi, thanks for your nice work. In your paper, you mentioned the best bin size is 30, which is a balanced value, what is the batch size in your experiments when you using bin size 30?

[libuyu]

@longchuan1985 We use the batch size of 16 (8 GPUs with two images per GPU), which can be seen in the example script. And I want to clarify that the relationship between the bin size and batch size is not so strong because the effect of bin size mainly depends on the distribution of the gradient norm of examples (but I admit larger batch size will make the distribution more steady).