Skip to content

[MRG+1] divide mnist features by 255 in mlp example#11961

Merged
rth merged 1 commit intoscikit-learn:masterfrom
amueller:mnist_filter_255
Sep 1, 2018
Merged

[MRG+1] divide mnist features by 255 in mlp example#11961
rth merged 1 commit intoscikit-learn:masterfrom
amueller:mnist_filter_255

Conversation

@amueller
Copy link
Copy Markdown
Member

Fixes #11960

@qinhanmin2014 qinhanmin2014 changed the title divide mnist features by 255 in mlp example [MRG+1] divide mnist features by 255 in mlp example Sep 1, 2018
@rth rth merged commit 2ab2927 into scikit-learn:master Sep 1, 2018
@jnothman
Copy link
Copy Markdown
Member

jnothman commented Sep 1, 2018 via email

@rth
Copy link
Copy Markdown
Member

rth commented Sep 1, 2018

Possibly in examples/linear_model/plot_sgd_early_stopping.py? Though that was already the case before fc56da5 unlike plot_mnist_filters.py I think..

@amueller
Copy link
Copy Markdown
Member Author

amueller commented Sep 1, 2018

@jnothman you introduced this in fc56da5 so I just wanted to undo that. For SGD it would probably be a good idea if there's no scaling but not as critical.

jnothman pushed a commit to jnothman/scikit-learn that referenced this pull request Sep 2, 2018
jnothman pushed a commit to jnothman/scikit-learn that referenced this pull request Sep 17, 2018
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

Successfully merging this pull request may close these issues.

4 participants