Skip to content
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

the validation set of top1 doesn't have a significant varaition, Is the training process right? #15

Open
xiaoming0217 opened this issue Jun 22, 2020 · 1 comment

Comments

@xiaoming0217
Copy link

as below

1592811599(1)

@earhian
Copy link
Owner

earhian commented Jun 24, 2020

step 1.
       freeze = False
       model_name = 'senet154'
       min_num_class = 10
       checkPoint_start = 0
       lr = 3e-4
       #until train map5 >= 0.98

step 2.
       freeze = True
       model_name = 'senet154'
       min_num_class = 0
       checkPoint_start = best checkPoint of step 1
       lr = 3e-4

step 3.
       freeze = True
       model_name = 'senet154'
       min_num_class = 0
       checkPoint_start = best checkPoint of step 2
       lr = 3e-5

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants