Skip to content
This repository has been archived by the owner on Sep 18, 2024. It is now read-only.

Doc for quantization #1881

Merged
merged 11 commits into from
Dec 29, 2019
Merged

Doc for quantization #1881

merged 11 commits into from
Dec 29, 2019

Conversation

Cjkkkk
Copy link
Contributor

@Cjkkkk Cjkkkk commented Dec 26, 2019

No description provided.

@QuanluZhang QuanluZhang changed the base branch from master to v1.3 December 27, 2019 01:15
@@ -30,6 +30,7 @@ We have provided several compression algorithms, including several pruning and q
| [Naive Quantizer](./Quantizer.md#naive-quantizer) | Quantize weights to default 8 bits |
| [QAT Quantizer](./Quantizer.md#qat-quantizer) | Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference. [Reference Paper](http://openaccess.thecvf.com/content_cvpr_2018/papers/Jacob_Quantization_and_Training_CVPR_2018_paper.pdf)|
| [DoReFa Quantizer](./Quantizer.md#dorefa-quantizer) | DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients. [Reference Paper](https://arxiv.org/abs/1606.06160)|
| [BNN Quantizer](./Quantizer.md#BNN-Quantizer) | Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1. [Reference Paper](https://arxiv.org/abs/1602.02830)|
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it's better to have a brief description of the concept Quantization before the table, same for Pruning

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I add a reference link to recent survey of model compression and brief introduction of Quantization and Pruning.

@leckie-chn leckie-chn mentioned this pull request Dec 27, 2019
19 tasks
@chicm-ms chicm-ms merged commit 9b49245 into microsoft:v1.3 Dec 29, 2019
@Cjkkkk Cjkkkk deleted the doc branch January 6, 2020 04:08
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants