Implement bidirectional GRU

mratsim / Arraymancer

A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends

https://mratsim.github.io/Arraymancer/

Apache License 2.0

1.34k stars 96 forks source link

Implement bidirectional GRU #281

Closed mratsim closed 6 years ago

mratsim commented 6 years ago

Following #272, unidirectional GRUs are implemented with stubs.

Next step is to add support for the reverse time direction. Ideally input shapes should be the same as PyTorch or Chainer.

mratsim commented 6 years ago

Forgot, duplicate #271