Einops v0.4.0: EinMix and torch.jit.script

Main Changes

• torch.jit.script is supported (in addition to previous torch.jit.trace)
• EinMix (swiss-knife for next-gen MLPs) is added. A much-improved einsum/linear layer is now available.
• einops.repeat in torch does not create copy when possible

Detailed PRs

• Update documentation by @arogozhnikov in #137
• Multiple updates in docs, add Rearrange layer to torch test by @arogozhnikov in #138
• Add support for torch scripting of einops layers by @arogozhnikov in #139
• Introduce EinMix - swiss-knife for next-gen MLPs by @arogozhnikov in #142
• Docs improvements: wording, visual style, EinMix by @arogozhnikov in #143
• Move docs to a separate folder by @arogozhnikov in #144
• Type hinting + add testing for EinMix composition/decomposition by @arogozhnikov in #154
• Reject repeated axes in parse_shape by @dmitriy-serdyuk in #159
• Enable ellipsis in patterns for parse_shape. by @dmitriy-serdyuk in #162

New Contributors

• @dmitriy-serdyuk made their first contribution in #159

Full Changelog: v0.3.2...v0.4.0

Einops v0.3.2: updated documentation and tutorials, keras -> tf.keras

• documentation and domain (#75, #76, #77, #79, #81), thanks to @cgarciae
• typos and spellcheck (thank @ollema and @GarrettMooney )
• moved away from keras to tf.keras
• adjustments to tutorials and testing
• other minor improvements

Einops v0.3: repeat + more friendly requirements + ...

• new operation: repeat (includes repeat/tiling logic, copying along a new dimension)
• anonymous axes (specified by their length not name) are allowed:

grayscale = reduce(image, 'h w 3 -> h w', 'mean')
image_with_identical_channels = repeat(grayscale, 'h w -> h w 3')

• 1 can be used to refer to all dimensions of length 1
• reduced restrictions on axes names: almost any python identified can be an axis name now
• reduction can be provided with callable not string
• tutorials were slightly updated to include these changes
• code in kernel undergone refactoring, and now more documented
• support: keras layers are deprecated in favor of tf.keras layers
• experimental layer introduced: WeightedEinsum (RFC: #71 )

Jax support + updated testing code

• experimental support for Jax framework was added
• testing code was rewritten and updated to work
• tf2 always worked with einops, but tests had to be updated. So, tests are updated for tf2
• tf readme, minor additions, comments, etc.

Thanks to contributors

Initial release (v0.1)

This release introduces einops, as well as its notion.

Initial release API:
Operations (ops)

• einops.rearrange and einops.reduce

Auxiliary

• einops.asnumpy and einops.parse_shape

Layers (for chainer, gluon, keras and torch)

• Rearrange and Reduce

Supported frameworks:

• numpy
• pytorch
• tensorflow eager
• cupy
• chainer
• gluon
• tensorflow
• mxnet (experimental)
• and keras (experimental)