Update 第十八章_后端架构选型、离线及实时计算.md
This commit is contained in:
parent
7f0a38ba6c
commit
fe05d65e82
|
|
@ -5,15 +5,15 @@
|
|||
Editor: 梁志成
|
||||
Contact: superzhicheng@foxmail.com
|
||||
|
||||
## 18.1 为什么需要模型压缩和加速?
|
||||
## 18.1 为什么需要分布式计算?
|
||||
|
||||
|
||||
## 18.2 目前有哪些深度学习模型压缩方法?
|
||||
## 18.2 目前有哪些分布式计算框架?
|
||||
|
||||
|
||||
### 18.2.1 前端压缩
|
||||
### 18.2.1 实时计算 $^2$
|
||||
|
||||
### 18.2.2 后端压缩
|
||||
### 18.2.2 离线计算
|
||||
|
||||
|
||||
## 18.3 目前有哪些深度学习模型优化加速方法?
|
||||
|
|
@ -22,5 +22,8 @@
|
|||
## 18.4 影响神经网络速度的4个因素(再稍微详细一点)
|
||||
|
||||
|
||||
## 18.6 参考文献
|
||||
|
||||
1. http://engineering.skymind.io/distributed-deep-learning-part-1-an-introduction-to-distributed-training-of-neural-networks
|
||||
2. http://engineering.skymind.io/distributed-deep-learning-part-1-an-introduction-to-distributed-training-of-neural-networks
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue