Open ascacdsaa opened 7 months ago
Thanks for your congratulations and attention to our work!
The pretraining time on our 8*3090GPUs for the DFormer are:
Model | DFormer-T | DFormer-S | DFormer-B | DFormer-L |
---|---|---|---|---|
Trianing Time | ~40h | ~49h | ~72h | ~85h |
The training time also depends on the CPUs. More CPUs can accelerate the training duration.
Congratulations on your paper being accepted. I am curious about your code. Did you use 8 3090s for pretraining on imagenet-1k? How many hours did you train in total?Looking forward to your reply!