码迷,mamicode.com
首页 > 其他好文 > 详细

Pytorch的runtime error

时间:2019-04-24 15:59:37      阅读:1923      评论:0      收藏:0      [点我收藏+]

标签:node   res   rap   back   div   pre   false   sha   shape   

RuntimeError: bool value of Tensor with more than one value is ambiguous

运行下面这段代码的时候出错了,后来网上搜说改成 if w1.grad is not None:  可以通过。  

#===========PyTorch: Autograd==============
#====A PyTorch Variable is a node in a computational graph===
#==============x.data is a Tensor
#=============x.grad is a Variable of gradients(same shape as x.data)==
#========x.grad.data is a Tensor of gradients===========================
import torch 
from torch.autograd import Variable
N,D_in, H,D_out = 64, 1000, 100, 10
x = Variable(torch.randn(N, D_in), requires_grad=False)
y = Variable(torch.randn(N, D_out), requires_grad=False)
w1 = Variable(torch.randn(D_in, H), requires_grad=True)
w2 = Variable(torch.randn(H,D_out), requires_grad=True)

learning_rate = 1e-6
for t in range(500):
  y_pred = x.mm(w1).clamp(min=0).mm(w2)
  loss = ((y_pred-y).pow(2).sum())
  #should be if w1.grad is not None:
  if w1.grad:
    w1.grad.data.zero_()
  if w2.grad: 
    w2.grad.data.zero_()
  loss.backward()
  
  w1.data -= learning_rate * w1.grad.data
  w2.data -= learning_rate * w2.grad.data
  print(loss)

 

Pytorch的runtime error

标签:node   res   rap   back   div   pre   false   sha   shape   

原文地址:https://www.cnblogs.com/Shinered/p/10762783.html

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!