pytorch-gradual-warmup-lr
pytorch-gradual-warmup-lr copied to clipboard
Userwarning solve and sample update
first
there are 2 userwarning.
- The epoch parameter in
scheduler.step()
was not necessary and is being deprecated where possible. Please usescheduler.step()
to step the scheduler. - To get the last learning rate computed by the scheduler, please use
get_last_lr()
.
I modified the code to make sure it met the requirements of pytorch
second
use warnup + CosineAnnearling as an sample,and plot the lr list. by the way, i update the readme