pytorch中如何只让指定变量向后传播梯度?
(或者说如何让指定变量不参与后向传播?)
有以下公式,假如要让L对xvar求导:
(1)中,L对xvar的求导将同时计算out1部分和out2部分;
(2)中,L对xvar的求导只计算out2部分,因为out1的requires_grad=False;
(3)中,L对xvar的求导只计算out1部分,因为out2的requires_grad=False;
验证如下:
#!/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,将变量的requires_grad设为False,即可让变量不参与梯度的后向传播;
但是不能直接将out1.requires_grad=False;
其实,Variable类型提供了detach()方法,所返回变量的requires_grad为False。
注意:如果out1和out2的requires_grad都为False的话,那么xvar.grad就出错了,因为梯度没有传到xvar
补充:
volatile=True表示这个变量不计算梯度, 参考: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.
以上这篇在pytorch中实现只让指定变量向后传播梯度就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。
免责声明:本站资源来自互联网收集,仅供用于学习和交流,请遵循相关法律法规,本站一切资源不代表本站立场,如有侵权、后门、不妥请联系本站删除!
更新日志
- 凤飞飞《我们的主题曲》飞跃制作[正版原抓WAV+CUE]
- 刘嘉亮《亮情歌2》[WAV+CUE][1G]
- 红馆40·谭咏麟《歌者恋歌浓情30年演唱会》3CD[低速原抓WAV+CUE][1.8G]
- 刘纬武《睡眠宝宝竖琴童谣 吉卜力工作室 白噪音安抚》[320K/MP3][193.25MB]
- 【轻音乐】曼托凡尼乐团《精选辑》2CD.1998[FLAC+CUE整轨]
- 邝美云《心中有爱》1989年香港DMIJP版1MTO东芝首版[WAV+CUE]
- 群星《情叹-发烧女声DSD》天籁女声发烧碟[WAV+CUE]
- 刘纬武《睡眠宝宝竖琴童谣 吉卜力工作室 白噪音安抚》[FLAC/分轨][748.03MB]
- 理想混蛋《Origin Sessions》[320K/MP3][37.47MB]
- 公馆青少年《我其实一点都不酷》[320K/MP3][78.78MB]
- 群星《情叹-发烧男声DSD》最值得珍藏的完美男声[WAV+CUE]
- 群星《国韵飘香·贵妃醉酒HQCD黑胶王》2CD[WAV]
- 卫兰《DAUGHTER》【低速原抓WAV+CUE】
- 公馆青少年《我其实一点都不酷》[FLAC/分轨][398.22MB]
- ZWEI《迟暮的花 (Explicit)》[320K/MP3][57.16MB]