@@ -73,12 +73,6 @@ All types of sampling strategies and their parameter are listed here:
* Which means the variable value is a value like `round(exp(normal(mu, sigma)) / q) * q`
* Suitable for a discrete variable with respect to which the objective is smooth and gets smoother with the size of the variable, which is bounded from one side.
* Type for [Neural Architecture Search Space][1]. Value is also a dictionary, which contains key-value pairs representing respectively name and search space of each mutable_layer.
* For now, users can only use this type of search space with annotation, which means that there is no need to define a json file for search space since it will be automatically generated according to the annotation in trial code.
* The following HPO tuners can be adapted to tune this search space: TPE, Random, Anneal, Evolution, Grid Search,
Hyperband and BOHB.
* For detailed usage, please refer to [General NAS Interfaces][1].
## Search Space Types Supported by Each Tuner
...
...
@@ -105,5 +99,3 @@ Known Limitations:
* Only Random Search/TPE/Anneal/Evolution tuner supports nested search space
* We do not support nested search space "Hyper Parameter" in visualization now, the enhancement is being considered in [#1110](https://github.com/microsoft/nni/issues/1110), any suggestions or discussions or contributions are warmly welcomed
在 ['PRUNING FILTERS FOR EFFICIENT CONVNETS'](https://arxiv.org/abs/1608.08710) 中提出,作者 Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet 以及 Hans Peter Graf。
NNI 提供了易于使用的工具包来帮助用户设计并使用压缩算法。 其使用了统一的接口来支持 TensorFlow 和 PyTorch。 只需要添加几行代码即可压缩模型。 NNI 中也内置了一些流程的模型压缩算法。 用户还可以通过 NNI 强大的自动调参功能来找到最好的压缩后的模型,详见[自动模型压缩](./AutoCompression.md)。 另外,用户还能使用 NNI 的接口,轻松定制新的压缩算法,详见[教程](#customize-new-compression-algorithms)。
| [FPGM Pruner](./Pruner.md#fpgm-pruner) | Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration [参考论文](https://arxiv.org/pdf/1811.00250.pdf) |
在 [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://arxiv.org/abs/1710.01878)中,作者 Michael Zhu 和 Suyog Gupta 提出了一种逐渐修建权重的算法。
这是一种迭代的 Pruner,在 [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://arxiv.org/abs/1710.01878)中,作者 Michael Zhu 和 Suyog Gupta 提出了一种逐渐修建权重的算法。
这是一种一次性的 Pruner,FPGM Pruner 是论文 [Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration](https://arxiv.org/pdf/1811.00250.pdf) 的实现
> 以前的方法使用 “smaller-norm-less-important” 准则来修剪卷积神经网络中规范值较小的。 本文中,分析了基于规范的准则,并指出其所依赖的两个条件不能总是满足:(1) 过滤器的规范偏差应该较大;(2) 过滤器的最小规范化值应该很小。 为了解决此问题,提出了新的过滤器修建方法,即 Filter Pruning via Geometric Median (FPGM),可不考虑这两个要求来压缩模型。 与以前的方法不同,FPGM 通过修剪冗余的,而不是相关性更小的部分来压缩 CNN 模型。
这是一种一次性的 Pruner,由 ['PRUNING FILTERS FOR EFFICIENT CONVNETS'](https://arxiv.org/abs/1608.08710) 提出,作者 Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet 和 Hans Peter Graf。