Thinc

🔴 Bug fixes

* Fix incorrect packaging of `thinc.neural.gpu_ops`, introduced in v6.8.1.
* Fix bad data type in `thinc.extra.search.MaxViolation`, which caused segfaults on some platforms.

✨ Major features and improvements

* Add new `foreach` layer combinator, which maps a layer across elements of a sequence.
* Add support for `predict` methods to more layers, for use during decoding.
* Improve correctness of batch normalization. Previously, some layers would force batch normalization to run in training mode, even during prediction. This led to decreased accuracy in some situations.
* Improved efficiency of `Maxout` layer.

🔴 Bug fixes

* Fix compiler flags for MSVC
* Remove unnecessary Chainer dependency. Now depends on Chainer's `cupy` package.
* Fix LSTM layer.
* Small bug fixes to beam search

✨ Major features and improvements

* Add SELU layer, from [Klambauer et al. (2017)](https://arxiv.org/pdf/1706.02515.pdf).
* Add parametric soft attention layer, as in [Yang et al. (2016)](https://www.cs.cmu.edu/~diyiy/docs/naacl16.pdf).
* New higher-order function `uniqued`, which wraps layers giving them a per-batch cache.
* Improve batch normalization, by tracking activation moving averages.

🔴 Bug fixes

* Fix GPU usage in pooling operations.
* Add optimized code for extracting ngram features.
* Improve CPU/GPU compatibility.
* Improve compatibility of `LinearModel` class.

👥 Contributors

Thanks to tammoippen for the pull request!

🔴 Bug fixes

* Convolution is now computed the same on CPU and GPU.

🔴 Bug fixes

* Make order of dicts stable when serializing model.

✨ Major features and improvements

* Temporarily revert change to CuPy.
* Improve efficiency of Adam optimizer.