Published June 25, 2018
| Version v0.2.0
Software
Open
Neural Network Distiller
Description
- PyTorch 0.4 support
- An implementation of Baidu's RNN pruning paper from ICLR 2017 Narang, Sharan & Diamos, Gregory & Sengupta, Shubho & Elsen, Erich. (2017). <i>Exploring Sparsity in Recurrent Neural Networks</i>. (https://arxiv.org/abs/1704.05119)
- Add a word language model pruning example using AGP and Baidu RNN pruning
- Quantization aware training (4-bit quantization)
- New models: pre-activation ResNet for ImageNet and CIFAR, and AlexNet with batch-norm
- New quantization documentation content
Files
NervanaSystems/distiller-v0.2.0.zip
Files
(21.1 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:661012107395b91072725c84c0eccbc0
|
21.1 MB | Preview Download |
Additional details
Related works
- Is supplement to
- https://github.com/NervanaSystems/distiller/tree/v0.2.0 (URL)