Sync Sequential.fit() with Model.fit() #8192
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
...instead of relying on implicit default value.
fchollet
reviewed
Oct 23, 2017
| @@ -247,12 +247,12 @@ def test_EarlyStopping_reuse(): | |||
| stopper = callbacks.EarlyStopping(monitor='acc', patience=patience) | |||
| weights = model.get_weights() | |||
|
|
|||
| hist = model.fit(data, labels, callbacks=[stopper]) | |||
| hist = model.fit(data, labels, callbacks=[stopper], epochs=20) | |||
There was a problem hiding this comment.
This would slow down the tests and should be set to a lower value (e.g. 10). Is this change related to the rest of the PR? Doesn't look like it is...
There was a problem hiding this comment.
Without this change (introduced in the second commit) tests fail (see first commit). Maybe this change is just papering over a real bug?
I chose epochs=20, because earlier in the same function epochs=20 is used. In the whole file, epochs=20 is used 8 times, and epochs=10 is used 0 times.
|
Put docstrings into a different PR #8233 |
|
@ozabluda I will take a look, thanks. |
nbam
pushed a commit
to nbam/keras
that referenced
this pull request
Nov 22, 2017
* Sync Sequential.fit() with Model.fit() * Specify explicit epochs=20 ...instead of relying on implicit default value. * Revert docstring changes * pep8 * pep8
nbam
pushed a commit
to nbam/keras
that referenced
this pull request
Nov 30, 2017
* Sync Sequential.fit() with Model.fit() * Specify explicit epochs=20 ...instead of relying on implicit default value. * Revert docstring changes * pep8 * pep8
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
... and improve docstrings.
A couple of API changes, all backward compatible (additions and more permissive), except that now Model.fit(epoch=1) is the default (matching Sequential.fit(). I didn't find any example/*.py affected by this.