Skip to content

Releases: kundajelab/deeplift

Removed another superfluous print statement

20 Aug 04:44
Compare
Choose a tag to compare
v0.6.6.2-alpha

version bumps

Removed batchnorm warning messages

20 Aug 04:31
Compare
Choose a tag to compare
Pre-release

Unit tests for batchnorm have been added for a while, but I hadn't removed the warning message.

Version on pypi

13 Jul 21:14
Compare
Choose a tag to compare
Version on pypi Pre-release
Pre-release

The version corresponding to what's on pypi.

Contains fix for conversion of PReLU layers.

12 Jul 22:21
a696ed6
Compare
Choose a tag to compare
Merge pull request #56 from kundajelab/prelu_fix

PReLU conversion fix

Keras 2 compatible version, with genomics notebooks in

04 Jul 06:54
Compare
Choose a tag to compare

Keras 2 compatible version based off the master branch.

Tagging version before making keras2compat the master branch

04 Jul 06:17
abf3aab
Compare
Choose a tag to compare

Making a tagged version before I replace the master branch with v6 contents.

v0.6.2 for Keras 2 and tensorflow backend

05 Jun 04:17
a1a074c
Compare
Choose a tag to compare

@jisraeli @annashcherbina here is a tagged version that you should be able to use. It passes unit tests for both python 2 and 3.

v0.5.1-theano

23 Apr 23:18
Compare
Choose a tag to compare
v0.5.1-theano Pre-release
Pre-release

Difference between 0.4.0 and 0.5.0 is functionality added to support separate treatment of positive and negative contributions for all activation functions (the "RevealCancel" rule - matches functionality in ICML submission). Difference between 0.5.1-theano and 0.5.0-theano (for which a release was not drafted) is that some support was added for border mode same and a cast to float32 was added to the integrated gradients function to account for cases where the supplied data might be uint8.

v0.4.0-alpha

12 Dec 06:06
Compare
Choose a tag to compare
v0.4.0-alpha Pre-release
Pre-release

Theano backend. 1d convolutions and pooling added. Sequential model conversion tested with keras 0.2, 0.3 and 1.1.2, and support for keras models trained with tensorflow dimension ordering is in place. No keras functional API conversion yet.

v0.3-alpha

01 Nov 23:10
Compare
Choose a tag to compare
v0.3-alpha Pre-release
Pre-release

Release for dragonn 0.1.2