Sitelet https://web.archive.org/web/20201124063157/https://github.com/keras-team/keras/issues/13652
Skip to content

/ keras

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

Jump to bottom

Confusing docs in model.fit #13652

Open
qiagu opened this issue Dec 24, 2019 · 4 comments
Open

Confusing docs in model.fit #13652

qiagu opened this issue Dec 24, 2019 · 4 comments
Labels
type:docs

Comments

@qiagu
Copy link
Contributor

@qiagu qiagu commented Dec 24, 2019

https://github.com/keras-team/keras/blob/master/keras/engine/training.py#L1071-L1077
There are two validation_steps.
@Lasers67
Copy link

@Lasers67 Lasers67 commented Dec 27, 2019

If validation_data is a generator, validation_steps define how many number of batches of validation needs to be done after training has happened,
If validation_data is data tensor, validation_steps can only be used when doing step wise training(or steps_per_epoch must be defined)
@qiagu
Copy link
Contributor Author

@qiagu qiagu commented Dec 28, 2019

Make sense now. Thanks @Lasers67
I feel the doc needs in a better format, doesn't it?
@Lasers67
Copy link

@Lasers67 Lasers67 commented Dec 28, 2019

Ya True willing to work on that.
@Lasers67 Lasers67 mentioned this issue Jan 1, 2020
Open
@rurajesh
Copy link

@rurajesh rurajesh commented Feb 17, 2020

Got confused by the same. Thanks for the clarification.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
type:docs
Projects
None yet
Milestone
No milestone
Linked pull requests

Successfully merging a pull request may close this issue.

None yet
4 participants
@rurajesh @Lasers67 @qiagu @amahendrakar
You can’t perform that action at this time.