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.

Sign up for GitHub

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

Jump to bottom

idlmam.py: learning rate parameter of train_simple_network is ignored #8

Open
medvedev opened this issue Mar 2, 2023 · 0 comments
Open

idlmam.py: learning rate parameter of train_simple_network is ignored #8

medvedev opened this issue Mar 2, 2023 · 0 comments

Comments

@medvedev
Copy link

medvedev commented Mar 2, 2023

Learning rate (named parameter lr) is ignored inside the train_simple_network function's body.
Instead, learning rate is hardcoded to 0.001 in line:

Inside-Deep-Learning/idlmam.py

Line 123 in bc4dccf

optimizer = torch.optim.SGD(model.parameters(), lr=0.001)

Solution: pass lr to the created optimizer
medvedev added a commit to medvedev/Inside-Deep-Learning that referenced this issue Mar 2, 2023
@medvedev
EdwardRaff#8 Proper use of lr parameter
a2caa73 
Use `lr` parameter provided to `train_simple_network(...)` when creating an optimizer
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@medvedev