New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
can not reproduce the performance of svt-small model #20
Comments
Thanks for your attention. |
Thanks for your quick reply! I don't try the global size = 1024. mmmm, sorry, I don't know what's mean of global size, maybe equal to the batch_size * the number of gpu devices? In the main.py, I find one line to revise the learning rate: To sum up, thanks for your reminder and your nice work again! |
Yes. Your setting is a global batch size of 2048. |
Hi, I am sorry to interrupt you again. Recently, I try to use below code to train the model "alt_gvt_small" that global_size=1024:
my logs: your logs: Maybe, I should set batch_size=256 and gpus=4? |
emm. |
Oh, sorry, So careless mistakes. I will clone a new one and try it again. |
Thanks for your nice work!
And I would like to reproduce the performance of svt-small(alt_gvt_small) model. Below is my code:
python -m torch.distributed.launch --nproc_per_node=8 --use_env main.py --model alt_gvt_small --batch-size 256 --data-path ../data/ImageNet --dist-eval --drop-path 0.2
The other parameters are default. But the result only up to 81.1%, not 81.7%.
Could you give me some suggestions on how to reproduce your nice performance from scratch?
The text was updated successfully, but these errors were encountered: