Skip to content
#

dnn

Here are 824 public repositories matching this topic...

garymm
garymm commented Jun 10, 2022

Currently code like this is repeated several times:

field = mapping.STORAGE_TENSOR_TYPE_TO_FIELD[
    mapping.TENSOR_TYPE_TO_STORAGE_TENSOR_TYPE[data_type]]
getattr(tensor, field)

This is repetitive and can be encapsulated in a helper function.
Also the name "storage tensor type" is misleading and has led to at least one bug.

We should:

  1. Add a function that does all this
good first issue
pytorch-kaldi

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.

  • Updated Mar 14, 2022
  • Python

Heterogeneous Run Time version of Caffe. Added heterogeneous capabilities to the Caffe, uses heterogeneous computing infrastructure framework to speed up Deep Learning on Arm-based heterogeneous embedded platform. It also retains all the features of the original Caffe architecture which users deploy their applications seamlessly.

  • Updated Oct 16, 2018
  • C++

Improve this page

Add a description, image, and links to the dnn topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the dnn topic, visit your repo's landing page and select "manage topics."

Learn more