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
hi there,
thanks for your great work!
I'm a little confused about those config files for different datasets, especially the margin parameter in it. If I want to train this model all from start, should I set it to True? what about other parameters like learning rate?
The text was updated successfully, but these errors were encountered:
For a new dataset, you also need to create a new config file to control the parameters more conveniently, otherwise you have to modify it in option.py every time you train or test.
Regardless of whether the value of margin is True or False, this will directly affect line 343 of model/resnet.py. Setting it to True means that m_p of formula 4 in the paper is not 0.
You should of course set this to True if you want to train the model from the start, otherwise it will become a vanilla method.
For other parameters, you can try to fine-tune them according to the dataset you are using.
If you have further questions, please open an issue.
hi there,
thanks for your great work!
I'm a little confused about those config files for different datasets, especially the
margin
parameter in it. If I want to train this model all from start, should I set it to True? what about other parameters like learning rate?The text was updated successfully, but these errors were encountered: