参考链接: torch.nn.Module.requires_grad_(requires_grad=True)
原文及翻译:
requires_grad_(requires_grad=True)
方法: requires_grad_(requires_grad=True)
Change if autograd should record operations on parameters in this module.
在当前这个网络模块中对自动梯度机制进行修改,设置是否需要对模块中参数的
操作进行记录.
This method sets the parameters’ requires_grad attributes in-place.
该方法对参数的requires_grad属性进行原地(in-place)修改.
This method is helpful for freezing part of the module for finetuning or training parts of a model individually (e.g., GAN training).
这个方法很有用,尤其是在冻结模块的部分结构进行微调的时候或者在单独训练模
型的各个部分的时候,在这些情形下这个方法很有用.
Parameters 参数
requires_grad (bool) – whether autograd should record
operations on parameters in this module. Default: True.
requires_grad (布尔类型) – 该变量指明自动梯度是否需要记录当前
模块的参数的操作.默认值是True.
Returns 函数返回
self 自身self
Return type 返回类型
Module 模块类型Module
PyTorch源代码:
代码实验展示:
import torch
import torch.nn as nn
torch.manual_seed(seed=20200910)
class Model(torch.nn.Module):
def __init__(self):
super(Model,self).__init__()
self.conv1=torch.nn.Sequential( # 输入torch.Size([64, 1, 28, 28])
torch.nn.Conv2d(1,64,kernel_size=3,stride=1,padding=1),
torch.nn.ReLU(), # 输出torch.Size([64, 64, 28, 28])
torch.nn.Conv2d(64,128,kernel_size=3,stride=1,padding=1), # 输出torch.Size([64, 128, 28, 28])
torch.nn.ReLU(),
torch.nn.MaxPool2d(stride=2,kernel_size=2) # 输出torch.Size([64, 128, 14, 14])
)
self.dense=torch.nn.Sequential( # 输入torch.Size([64, 14*14*128])
torch.nn.Linear(14*14*128,1024), # 输出torch.Size([64, 1024])
torch.nn.ReLU(),
torch.nn.Dropout(p=0.5),
torch.nn.Linear(1024,10) # 输出torch.Size([64, 10])
)
self.layer4cxq1 = torch.nn.Conv2d(2,33,4,4)
self.layer4cxq2 = torch.nn.ReLU()
self.layer4cxq3 = torch.nn.MaxPool2d(stride=2,kernel_size=2)
self.layer4cxq4 = torch.nn.Linear(14*14*128,1024)
self.layer4cxq5 = torch.nn.Dropout(p=0.8)
self.attribute4cxq = nn.Parameter(torch.tensor(20200910.0))
self.attribute4lzq = nn.Parameter(torch.tensor([2.0,3.0,4.0,5.0]))
self.attribute4hh = nn.Parameter(torch.randn(3,4,5,6))
self.attribute4wyf = nn.Parameter(torch.randn(7,8,9,10))
def forward(self,x): # torch.Size([64, 1, 28, 28])
x = self.conv1(x) # 输出torch.Size([64, 128, 14, 14])
x = x.view(-1,14*14*128) # torch.Size([64, 14*14*128])
x = self.dense(x) # 输出torch.Size([64, 10])
return x
print('cuda(GPU)是否可用:',torch.cuda.is_available())
print('torch的版本:',torch.__version__)
model = Model() #.cuda()
print('调用方法requires_grad_(False)之前'.center(100,'-'))
print(model.layer4cxq1.weight.requires_grad)
model.requires_grad_(False)
print('调用方法requires_grad_(False)之后'.center(100,'-'))
print(model.layer4cxq1.weight.requires_grad)
model.requires_grad_()
print('调用方法requires_grad_()之后'.center(100,'-'))
print(model.layer4cxq1.weight.requires_grad)
控制台输出结果:
Windows PowerShell
版权所有 (C) Microsoft Corporation。保留所有权利。
尝试新的跨平台 PowerShell https://aka.ms/pscore6
加载个人及系统配置文件用了 943 毫秒。
(base) PS C:\Users\chenxuqi\Desktop\News4cxq\test4cxq> conda activate ssd4pytorch1_2_0
(ssd4pytorch1_2_0) PS C:\Users\chenxuqi\Desktop\News4cxq\test4cxq> & 'D:\Anaconda3\envs\ssd4pytorch1_2_0\python.exe' 'c:\Users\chenxuqi\.vscode\extensions\ms-python.python-2020.12.424452561\pythonFiles\lib\python\debugpy\launcher' '50225' '--' 'c:\Users\chenxuqi\Desktop\News4cxq\test4cxq\test2.py'
cuda(GPU)是否可用: True
torch的版本: 1.2.0+cu92
------------------------------------调用方法requires_grad_(False)之前-------------------------------------
True
------------------------------------调用方法requires_grad_(False)之后-------------------------------------
False
---------------------------------------调用方法requires_grad_()之后---------------------------------------
True
(ssd4pytorch1_2_0) PS C:\Users\chenxuqi\Desktop\News4cxq\test4cxq>