How to change the config to train Benchmarking-ViT-B with batch size 16 ?
Yingdong-Hu opened this issue · 2 comments
Hi, thanks for the great project!
How is this max_iter=184375
in Benchmarking-ViT-B calculated ? (num_images * epochs) / batch_size ?
I want to train a Benchmarking-ViT-B model with batch size 16 on 8-GPUs environment, but I am confused by the config file.
Could you advise how to adjust hyper-parameters like max_iter
, eval_period
if I change the batch size to 16?
MIMDet/configs/benchmarking/benchmarking_mask_rcnn_base_FPN_100ep_LSJ_mae.py
Lines 150 to 163 in 9e1dea1
Hi @Alxead, thanks for your interest in our work.
You are right: max_iter = (num_images * epochs) / batch_size
(num_images = ~118000
for COCO).
I suggest you change max_iter = 184375 * 4
& eval_period = 1844 * 4
if your bsz = 16
.
Also, I recommend changing the lr = 4e-5
.
But notice that this config cannot guarantee to re-produce the original accuracy.
I believe the issue at hand was addressed, as such I'm closing this. Feel free to ask if you have further questions.