learning
/
DeepLearning-500-questions
mirror of https://github.com/scutan90/DeepLearning-500-questions.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

update

This commit is contained in:
scutan90 2019-04-30 15:03:20 +08:00
parent ed063697d8
commit e171561304
2 changed files with 0 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
13-16章.docx Normal file
View File

Binary file not shown.

2
ch17_模型压缩、加速及移动端部署/第十七章_模型压缩、加速及移动端部署.md
View File

@ -292,7 +292,6 @@ Group convolution是将输入特征的维度c1分成g份，每个group对应的c
Group convolution计算方式如下： Group convolution计算方式如下：
![image](./img/ch17/2.png) ![image](./img/ch17/2.png)
Group convolution运算量为： Group convolution运算量为：
$$ $$
B = H * W * h1 * w1 * c1/g * c2/g * g B = H * W * h1 * w1 * c1/g * c2/g * g
$$ $$
@ -322,7 +321,6 @@ $$
PW卷积的计算方式如下： PW卷积的计算方式如下：
![image](./img/ch17/5.png) ![image](./img/ch17/5.png)
$$ $$
B_PW = H_m * W_m * 1 * 1 * c_1 * c_2 B_PW = H_m * W_m * 1 * 1 * c_1 * c_2
$$ $$