当前位置:网站首页>Named in pytoch_ parameters、named_ children、named_ Modules function
Named in pytoch_ parameters、named_ children、named_ Modules function
2022-04-23 15:43:00 【If you encounter a barrier, you have to step over it】
named_parameters function
- Returns... As an iterator model All the parameters in , The return value is one
Dictionaries
: containName of parameter
andValue size
; - Used in internal implementation
A recursive algorithm
, So for nested network parameters , MeetingRecursive traversal
, OutputBottom layer parameters
, See the following example ;
named_children() function
- This function is used to output the data in the network
Layer 1 module name and instance object
, Only the top module name will be displayed ;
named_modules() function
- This function is used to recursively output the data in the network
Module name and instance object of each layer
, The first mock exam will display the name of each module in all layers.
Example
import torch
import torch.nn as nn
class TestModel(nn.Module):
def __init__(self):
super(TestModel,self).__init__()
# Conventional convolution layer , The input channel is 3, The output channel is 12
self.conv1 = nn.Conv2d(3, 12, kernel_size=3, padding=1)
self.layer1 = nn.Sequential(
nn.Conv2d(12, 6, kernel_size=3, padding=1),
nn.Conv2d(6, 6, kernel_size=3, padding=1),
nn.ReLU(inplace=True)
)
def forward(self, x):
x = self.conv1(x)
x = self.layer1(x)
model = TestModel()
named_parameters = model.named_parameters()
print('------------parameters-----------------')
for name, parameter in named_parameters:
print(name)
named_children = model.named_children()
print('------------parameters-----------------')
for name, children in named_children:
print(name)
named_modules = model.named_modules()
print('------------modules-----------------')
for name, module in named_modules:
print(name)
------------ Output --------------------------
------------parameters-----------------
conv1.weight
conv1.bias
layer1.0.weight # You can see that for sequential The modules in the module are given a numeric number
layer1.0.bias
layer1.1.weight
layer1.1.bias
------------parameters-----------------
conv1
layer1
------------modules-----------------
conv1
layer1
layer1.0
layer1.1
layer1.2
版权声明
本文为[If you encounter a barrier, you have to step over it]所创,转载请带上原文链接,感谢
https://yzsam.com/2022/04/202204231532210552.html
边栏推荐
- Best practices of Apache APIs IX high availability configuration center based on tidb
- 一刷312-简单重复set-剑指 Offer 03. 数组中重复的数字(e)
- c语言---字符串+内存函数
- Upgrade MySQL 5.1 to 5.67
- 群体智能自主作业智慧农场项目启动及实施方案论证会议
- Crawling fragment of a button style on a website
- IronPDF for . NET 2022.4.5455
- How to test mobile app?
- 自主作业智慧农场创新论坛
- What if the package cannot be found
猜你喜欢
随机推荐
字符串最后一个单词的长度
Cookie&Session
s16.基于镜像仓库一键安装containerd脚本
Application of Bloom filter in 100 million flow e-commerce system
Why is IP direct connection prohibited in large-scale Internet
cadence SPB17. 4 - Active Class and Subclass
MySQL Cluster Mode and application scenario
【递归之数的拆分】n分k,限定范围的拆分
Load Balancer
【backtrader源码解析18】yahoo.py 代码注释及解析(枯燥,对代码感兴趣,可以参考)
码住收藏▏软件测试报告模板范文来了
【Leetcode-每日一题】安装栅栏
[leetcode daily question] install fence
Extract non duplicate integers
Why disable foreign key constraints
Codejock Suite Pro v20.3.0
Independent operation smart farm Innovation Forum
Demonstration meeting on startup and implementation scheme of swarm intelligence autonomous operation smart farm project
推荐搜索 常用评价指标
【AI周报】英伟达用AI设计芯片;不完美的Transformer要克服自注意力的理论缺陷