PaddleSlim is a toolkit for model compression. It contains a collection of compression strategies, such as pruning, fixed point quantization, knowledge distillation, hyperparameter searching and neural architecture search.
PaddleSlim provides solutions of compression on computer vision models, such as image classification, object detection and semantic segmentation. Meanwhile, PaddleSlim Keeps exploring advanced compression strategies for language model. Furthermore, benckmark of compression strategies on some open tasks is available for your reference.
PaddleSlim also provides auxiliary and primitive API for developer and researcher to survey, implement and apply the method in latest papers. PaddleSlim will support developer in ability of framework and technology consulting.
- Automated pruning based evolution search strategy
- Support pruning of various deep architectures such as VGG, ResNet, and MobileNet.
- Support self-defined range of pruning, i.e., layers to be pruned.
- 模型剪裁
- 卷积通道均匀剪裁
- 基于敏感度的卷积通道剪裁
- 基于进化算法的自动剪裁
### Fixed Point Quantization
- 定点量化
- 在线量化训练（training aware）
- 离线量化（post training）
-**Training aware**
- Dynamic strategy: During inference, we quantize models with hyperparameters dynamically estimated from small batches of samples.
- Static strategy: During inference, we quantize models with the same hyperparameters estimated from training data.
- Support layer-wise and channel-wise quantization.
-**Post training**
- 知识蒸馏
- 支持单进程知识蒸馏
- 支持多进程分布式知识蒸馏
### Knowledge Distillation
- 神经网络结构自动搜索（NAS）
- 支持基于进化算法的轻量神经网络结构自动搜索
- 支持One-Shot网络结构自动搜索
- 支持 FLOPS / 硬件延时约束
- 支持多平台模型延时评估
- 支持用户自定义搜索算法和搜索空间
-**Naive knowledge distillation:** transfers dark knowledge by merging the teacher and student model into the same Program
-**Paddle large-scale scalable knowledge distillation framework Pantheon:** a universal solution for knowledge distillation, more flexible than the naive knowledge distillation, and easier to scale to the large-scale applications.
## 安装
- Decouple the teacher and student models --- they run in different processes in the same or different nodes, and transfer knowledge via TCP/IP ports or local files;
- Friendly to assemble multiple teacher models and each of them can work in either online or offline mode independently;
- Merge knowledge from different teachers and make batch data for the student model automatically;
- Support the large-scale knowledge prediction of teacher models on multiple devices.
### Neural Architecture Search
- Neural architecture search based on evolution strategy.
- Support distributed search.
- One-Shot neural architecture search.
- Support FLOPs and latency constrained search.
- Support the latency estimation on different hardware and platforms.
## Install
Requires:
依赖：
Paddle >= 1.7.0
...
...
@@ -56,52 +46,53 @@ Paddle >= 1.7.0
pip install paddleslim -i https://pypi.org/simple
```
## Usage
## 使用
-[QuickStart](docs/zh_cn/quick_start): Introduce how to use PaddleSlim by simple examples.
-[Advanced Tutorials](docs/zh_cn/tutorials)：Tutorials about advanced usage of PaddleSlim.
-[Model Zoo](docs/zh_cn/model_zoo.md)：Benchmark and pretrained models.
PaddleSlim is a toolkit for model compression. It contains a collection of compression strategies, such as pruning, fixed point quantization, knowledge distillation, hyperparameter searching and neural architecture search.
PaddleSlim provides solutions of compression on computer vision models, such as image classification, object detection and semantic segmentation. Meanwhile, PaddleSlim Keeps exploring advanced compression strategies for language model. Furthermore, benckmark of compression strategies on some open tasks is available for your reference.
PaddleSlim also provides auxiliary and primitive API for developer and researcher to survey, implement and apply the method in latest papers. PaddleSlim will support developer in ability of framework and technology consulting.
## Features
### Pruning
- Uniform pruning of convolution
- Sensitivity-based prunning
- Automated pruning based evolution search strategy
- Support pruning of various deep architectures such as VGG, ResNet, and MobileNet.
- Support self-defined range of pruning, i.e., layers to be pruned.
### Fixed Point Quantization
-**Training aware**
- Dynamic strategy: During inference, we quantize models with hyperparameters dynamically estimated from small batches of samples.
- Static strategy: During inference, we quantize models with the same hyperparameters estimated from training data.
- Support layer-wise and channel-wise quantization.
-**Post training**
### Knowledge Distillation
-**Naive knowledge distillation:** transfers dark knowledge by merging the teacher and student model into the same Program
-**Paddle large-scale scalable knowledge distillation framework Pantheon:** a universal solution for knowledge distillation, more flexible than the naive knowledge distillation, and easier to scale to the large-scale applications.
- Decouple the teacher and student models --- they run in different processes in the same or different nodes, and transfer knowledge via TCP/IP ports or local files;
- Friendly to assemble multiple teacher models and each of them can work in either online or offline mode independently;
- Merge knowledge from different teachers and make batch data for the student model automatically;
- Support the large-scale knowledge prediction of teacher models on multiple devices.
### Neural Architecture Search
- Neural architecture search based on evolution strategy.
- Support distributed search.
- One-Shot neural architecture search.
- Support FLOPs and latency constrained search.
- Support the latency estimation on different hardware and platforms.
## Install
Requires:
Paddle >= 1.7.0
```bash
pip install paddleslim -i https://pypi.org/simple
```
## Usage
-[QuickStart](docs/zh_cn/quick_start): Introduce how to use PaddleSlim by simple examples.
-[Advanced Tutorials](docs/zh_cn/tutorials)：Tutorials about advanced usage of PaddleSlim.
-[Model Zoo](docs/zh_cn/model_zoo.md)：Benchmark and pretrained models.
-[Algorithm Background](https://paddlepaddle.github.io/PaddleSlim/algo/algo.html): Introduce the background of quantization, pruning, distillation, NAS.
-[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/tree/master/slim): Introduce how to use PaddleSlim in PaddleDetection library.
-[PaddleSeg](https://github.com/PaddlePaddle/PaddleSeg/tree/develop/slim): Introduce how to use PaddleSlim in PaddleSeg library.
-[PaddleLite](https://paddlepaddle.github.io/Paddle-Lite/): How to use PaddleLite to deploy models generated by PaddleSlim.
