Baseline training configs
hanoonaR opened this issue · 1 comments
hanoonaR commented
Hi,
Thank you for sharing your work. I would to like know the training configurations used in your baseline reported in Table 2 in your paper. The implementation details in the paper specifies 1x schedule with lr of 0.02. However, the samples_per_gpu
is set to 4 in the shared configuration,
Could you please specify the the number of GPU's and the batch size and corresponding lr used in your baseline.
Thank you.
fcjian commented
Thank you for your suggestion.
The baseline reported in Table 2 is trained with batch size of 16 (4 x 4) on 4 GPUs and lr of 0.02.