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

How to control the training epochs in the codes ? #48

Closed
sdlpkxd opened this issue Jun 24, 2019 · 2 comments
Closed

How to control the training epochs in the codes ? #48

sdlpkxd opened this issue Jun 24, 2019 · 2 comments

Comments

@sdlpkxd
Copy link

sdlpkxd commented Jun 24, 2019

Excuse me
In the code we can control the loop by the parameter iterations, but how can we know how many epochs we trained ?
Thanks in advance

@sdlpkxd sdlpkxd changed the title How to control the training epochs the codes ? How to control the training epochs the in the codes ? Jun 24, 2019
@sdlpkxd sdlpkxd changed the title How to control the training epochs the in the codes ? How to control the training epochs in the codes ? Jun 24, 2019
@kong1060553768
Copy link

Iterations are iterations, which are shown by tqdm! By the way, how was your training result?

@jmiller656
Copy link
Owner

My current data utilities don't calculate epochs based on your dataset size, so you'd have to do some math to carefully decide the number of training iterations instead.

This may be fixed in a future version where I switch the library to keras

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

3 participants