Skip to content

Commit 8169858

Browse files
alanchiaotensorflower-gardener
authored andcommitted
Create RELEASE.md file for release notes.
People creating PRs will be responsible for updating the release notes themselves, for major features and bug fixes. Whatever is in the release notes at the time of a release will go out, with some possible editing. PiperOrigin-RevId: 321267749
1 parent 939bed8 commit 8169858

File tree

2 files changed

+29
-0
lines changed

2 files changed

+29
-0
lines changed

CONTRIBUTING.md

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -32,6 +32,9 @@ See these [guidelines](CONTRIBUTING_TECHNIQUE.md).
3232

3333
Please wait until we finish this section.
3434

35+
New features and bug fixes for documented features should come with a
36+
modification to the [release notes](RELEASE.md).
37+
3538
## Code reviews
3639

3740
All submissions, including submissions by project members, require review. We

RELEASE.md

Lines changed: 26 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,26 @@
1+
<!--
2+
See https://github.com/tensorflow/model-optimization/releases/ for previous
3+
examples of release notes. This project follows https://semver.org/.
4+
5+
"Tested against" references the versions of TensorFlow that TFMOT unit tests
6+
will be run against prior to release. For 2.X, only the earliest (2.0.0) and latest (nightly)
7+
TF releases are tested against, under the assumption that everything in between
8+
works sufficiently well enough.
9+
-->
10+
11+
# Release following 0.3.0
12+
13+
Keras quantization API:
14+
15+
* Major Features and Improvements
16+
*
17+
* Bug Fixes and Other Changes
18+
* Fixed Sequential model support for BatchNorm layers that follow Conv/DepthwiseConv ([issue](https://github.com/tensorflow/model-optimization/issues/378)).
19+
* Improved error message for not using `quantize_scope` with custom Keras layers and objects.
20+
* Tested against TensorFlow nightly
21+
22+
Keras pruning API:
23+
24+
* Tested against TensorFlow 1.14.0, 2.0.0, and nightly.
25+
26+

0 commit comments

Comments
 (0)