Skip to content

Commit 8dac88d

Browse files
authored
Release v0.2.3
* Update version to v0.2.3 * Update CHANGELOG * Update `examples/text_style_transfer` README
2 parents 46e006f + f4c04af commit 8dac88d

File tree

3 files changed

+9
-2
lines changed

3 files changed

+9
-2
lines changed

CHANGELOG.md

Lines changed: 6 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,13 +1,18 @@
11

2-
## [Unreleased]
2+
## [v0.2.3](https://github.com/asyml/texar/releases/tag/v0.2.3) (2019-09-22)
33

44
### New features
55

6+
* Texar Tensorflow now imported by `import texar.tf as tx`. ([#197](https://github.com/asyml/texar/pull/197))
7+
* Add pretrained modules \[[docs](https://texar.readthedocs.io/en/latest/code/modules.html#pre-trained)\], e.g., BERT, XLNet, etc. ([#206](https://github.com/asyml/texar/pull/206))
8+
* Add new tensor shape related utils, e.g., [reduce_with_weights](https://texar.readthedocs.io/en/latest/code/utils.html#reduce-with-weights), [varlength\_\*](https://texar.readthedocs.io/en/latest/code/utils.html#varlength-concat). ([#201](https://github.com/asyml/texar/pull/201))
9+
610
### Feature improvements
711

812
### Fixes
913

1014
* Fix docstring of connector `_mlp_transform`. ([#192](https://github.com/asyml/texar/pull/192))
15+
* Fix `dynamic_decode` out-of-range error when max-decoding-length is reached. ([#208](https://github.com/asyml/texar/pull/208))
1116

1217
## [v0.2.2](https://github.com/asyml/texar/releases/tag/v0.2.2) (2019-08-05)
1318

examples/text_style_transfer/README.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -31,6 +31,8 @@ python main.py --config config
3131
* The model will first be pre-trained for a few epochs (specified in `config.py`). During pre-training, the `Encoder-Decoder` part is trained as an autoencoder, while the `Classifier` part is trained with the classification labels.
3232
* Full-training is then performed for another few epochs. During full-training, the `Classifier` part is fixed, and the `Encoder-Decoder` part is trained to fit the classifier, along with continuing to minimize the autoencoding loss.
3333

34+
(**Note:** When using your own dataset, make sure to set `max_decoding_length_train` and `max_decoding_length_infer` in [config.py](https://github.com/asyml/texar/blob/master/examples/text_style_transfer/config.py#L85-L86).)
35+
3436
Training log is printed as below:
3537
```
3638
gamma: 1.0, lambda_g: 0.0

texar/tf/version.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -14,7 +14,7 @@
1414

1515
_MAJOR = "0"
1616
_MINOR = "2"
17-
_REVISION = "3-unreleased"
17+
_REVISION = "3"
1818

1919
VERSION_SHORT = "{0}.{1}".format(_MAJOR, _MINOR)
2020
VERSION = "{0}.{1}.{2}".format(_MAJOR, _MINOR, _REVISION)

0 commit comments

Comments
 (0)