You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Now I faced a couple of problems: there are no such modules as "constants", "utils" and etc, but its not a major problem. I'm trying to run main_fpn.py with python main_fpn.py --epochs 40 --cuda --bs 4 --num_workers 3 --output_dir output_dir/, but only got NaN's as output from network and as values of losses.
Could you please write more detailed instructions how to run your code?
The text was updated successfully, but these errors were encountered:
Download the net_utils.py, or just define the adjust_learning_rate function
defadjust_learning_rate(optimizer, decay=0.1):
"""Sets the learning rate to the initial LR decayed by 0.5 every 20 epochs"""forparam_groupinoptimizer.param_groups:
param_group['lr'] =decay*param_group['lr']
Now I faced a couple of problems: there are no such modules as "constants", "utils" and etc, but its not a major problem. I'm trying to run main_fpn.py with
python main_fpn.py --epochs 40 --cuda --bs 4 --num_workers 3 --output_dir output_dir/
, but only got NaN's as output from network and as values of losses.Could you please write more detailed instructions how to run your code?
The text was updated successfully, but these errors were encountered: