Contents

## 0.1.4 (2019-12-01)

- Added distance functions
- Added more activations
- Added more linear layers
- Added more loss functions
- Added more init methods
- Added support for tensor assignment

## 0.1.3 (2019-11-30)

- Changed to BSD 3-Clause license to match PyTorch
- Added many optimizers
- Added `StepLR` learning rate scheduler
- Added dropout
- Added embedding
- Added support for `bool` type
- Improved performance of `from_numo`

## 0.1.2 (2019-11-27)

- Added SGD optimizer
- Added support for gradient to `backward` method
- Added `argmax`, `eq`, `leaky_relu`, `prelu`, and `reshape` methods
- Improved indexing
- Fixed `zero_grad`
- Fixed error with infinite values

## 0.1.1 (2019-11-26)

- Added support for `uint8` and `int8` types
- Fixed `undefined symbol` error on Linux
- Fixed C++ error messages

## 0.1.0 (2019-11-26)

- First release

Version data entries

1 entries across 1 versions & 1 rubygems

Version	Path
torch-rb-0.1.4	CHANGELOG.md