在pytorch中實現(xiàn)只讓指定變量向后傳播梯度

更新時間：2020年02月29日 10:43:26 作者：美利堅節(jié)度使

今天小編就為大家分享一篇在pytorch中實現(xiàn)只讓指定變量向后傳播梯度，具有很好的參考價值，希望對大家有所幫助。一起跟隨小編過來看看吧

pytorch中如何只讓指定變量向后傳播梯度？

（或者說如何讓指定變量不參與后向傳播？）

有以下公式，假如要讓L對xvar求導(dǎo)：

（1）中，L對xvar的求導(dǎo)將同時計算out1部分和out2部分；

（2）中，L對xvar的求導(dǎo)只計算out2部分，因為out1的requires_grad=False；

（3）中，L對xvar的求導(dǎo)只計算out1部分，因為out2的requires_grad=False；

驗證如下：

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Wed May 23 10:02:04 2018
@author: hy
"""
 
import torch
from torch.autograd import Variable
print("Pytorch version: {}".format(torch.__version__))
x=torch.Tensor([1])
xvar=Variable(x,requires_grad=True)
y1=torch.Tensor([2])
y2=torch.Tensor([7])
y1var=Variable(y1)
y2var=Variable(y2)
#(1)
print("For (1)")
print("xvar requres_grad: {}".format(xvar.requires_grad))
print("y1var requres_grad: {}".format(y1var.requires_grad))
print("y2var requres_grad: {}".format(y2var.requires_grad))
out1 = xvar*y1var
print("out1 requres_grad: {}".format(out1.requires_grad))
out2 = xvar*y2var
print("out2 requres_grad: {}".format(out2.requires_grad))
L=torch.pow(out1-out2,2)
L.backward()
print("xvar.grad: {}".format(xvar.grad))
xvar.grad.data.zero_()
#(2)
print("For (2)")
print("xvar requres_grad: {}".format(xvar.requires_grad))
print("y1var requres_grad: {}".format(y1var.requires_grad))
print("y2var requres_grad: {}".format(y2var.requires_grad))
out1 = xvar*y1var
print("out1 requres_grad: {}".format(out1.requires_grad))
out2 = xvar*y2var
print("out2 requres_grad: {}".format(out2.requires_grad))
out1 = out1.detach()
print("after out1.detach(), out1 requres_grad: {}".format(out1.requires_grad))
L=torch.pow(out1-out2,2)
L.backward()
print("xvar.grad: {}".format(xvar.grad))
xvar.grad.data.zero_()
#(3)
print("For (3)")
print("xvar requres_grad: {}".format(xvar.requires_grad))
print("y1var requres_grad: {}".format(y1var.requires_grad))
print("y2var requres_grad: {}".format(y2var.requires_grad))
out1 = xvar*y1var
print("out1 requres_grad: {}".format(out1.requires_grad))
out2 = xvar*y2var
print("out2 requres_grad: {}".format(out2.requires_grad))
#out1 = out1.detach()
out2 = out2.detach()
print("after out2.detach(), out2 requres_grad: {}".format(out1.requires_grad))
L=torch.pow(out1-out2,2)
L.backward()
print("xvar.grad: {}".format(xvar.grad))
xvar.grad.data.zero_()

pytorch中，將變量的requires_grad設(shè)為False，即可讓變量不參與梯度的后向傳播；

但是不能直接將out1.requires_grad=False;

其實，Variable類型提供了detach()方法，所返回變量的requires_grad為False。

注意：如果out1和out2的requires_grad都為False的話，那么xvar.grad就出錯了，因為梯度沒有傳到xvar

補充：

volatile=True表示這個變量不計算梯度, 參考:Volatile is recommended for purely inference mode, when you're sure you won't be even calling .backward(). It's more efficient than any other autograd setting - it will use the absolute minimal amount of memory to evaluate the model. volatile also determines that requires_grad is False.

以上這篇在pytorch中實現(xiàn)只讓指定變量向后傳播梯度就是小編分享給大家的全部內(nèi)容了，希望能給大家一個參考，也希望大家多多支持腳本之家。

您可能感興趣的文章: