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

[Bugfix][Keras] axis of softmax #3834

Merged
merged 1 commit into from
Aug 28, 2019
Merged

Conversation

yongwww
Copy link
Member

@yongwww yongwww commented Aug 26, 2019

@kevinthesun kevinthesun merged commit 07a83a6 into apache:master Aug 28, 2019
@kevinthesun
Copy link
Contributor

Thanks!

@@ -117,7 +117,16 @@ def _convert_advanced_activation(inexpr, keras_layer, etab):
act_type = type(keras_layer).__name__

if act_type == 'Softmax':
return _op.nn.softmax(inexpr, axis=1)
axis = keras_layer.axis
dims = len(keras_layer.input_shape)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

dims is needed in one particular case below. This line can be moved to the place where dims is used

wweic pushed a commit to wweic/tvm that referenced this pull request Sep 16, 2019
wweic pushed a commit to wweic/tvm that referenced this pull request Sep 16, 2019
wweic pushed a commit to neo-ai/tvm that referenced this pull request Sep 16, 2019
@yongwww yongwww deleted the keras-bugs branch December 8, 2020 12:58
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.

3 participants