Python Pytorch 1.5优化器导致.step()中的就地操作(可能存在错误)
关于。PyTorch提到了这一变化,但我不确定如何应用他们的指导方针,可能只是有一个bug 此代码将显示错误Python Pytorch 1.5优化器导致.step()中的就地操作(可能存在错误),python,pytorch,Python,Pytorch,关于。PyTorch提到了这一变化,但我不确定如何应用他们的指导方针,可能只是有一个bug 此代码将显示错误 import torch import torch.nn as nn import numpy as np import matplotlib.pyplot as plt # Hyper Parameters BATCH_SIZE = 64 LR_G = 0.0001 LR_D = 0.0001 N_IDEAS = 5 ART_COMPONENTS = 15 PAINT_PO
import torch
import torch.nn as nn
import numpy as np
import matplotlib.pyplot as plt
# Hyper Parameters
BATCH_SIZE = 64
LR_G = 0.0001
LR_D = 0.0001
N_IDEAS = 5
ART_COMPONENTS = 15
PAINT_POINTS = np.vstack([np.linspace(-1, 1, ART_COMPONENTS) for _ in range(BATCH_SIZE)])
def artist_works(): # painting from the famous artist (real target)
r = 0.02 * np.random.randn(1, ART_COMPONENTS)
paintings = np.sin(PAINT_POINTS * np.pi) + r
paintings = torch.from_numpy(paintings).float()
return paintings
G = nn.Sequential( # Generator
nn.Linear(N_IDEAS, 128), # random ideas (could from normal distribution)
nn.ReLU(),
nn.Linear(128, ART_COMPONENTS), # making a painting from these random ideas
)
D = nn.Sequential( # Discriminator
nn.Linear(ART_COMPONENTS, 128), # receive art work either from the famous artist or a newbie like G
nn.ReLU(),
nn.Linear(128, 1),
nn.Sigmoid(), # tell the probability that the art work is made by artist
)
opt_D = torch.optim.Adam(D.parameters(), lr=LR_D)
opt_G = torch.optim.Adam(G.parameters(), lr=LR_G)
for step in range(10000):
artist_paintings = artist_works() # real painting from artist
G_ideas = torch.randn(BATCH_SIZE, N_IDEAS) # random ideas
G_paintings = G(G_ideas) # fake painting from G (random ideas)
prob_artist0 = D(artist_paintings) # D try to increase this prob
prob_artist1 = D(G_paintings) # D try to reduce this prob
D_loss = - torch.mean(torch.log(prob_artist0) + torch.log(1. - prob_artist1))
G_loss = torch.mean(torch.log(1. - prob_artist1))
opt_D.zero_grad()
D_loss.backward(retain_graph=True) # reusing computational graph
opt_D.step()
opt_G.zero_grad()
G_loss.backward()
opt_G.step()
RuntimeError:梯度计算所需的变量之一已通过就地操作修改:[torch.FloatTensor[128,1]],它是TBackward的输出0,处于版本4;应改用版本3。
唯一的[128,1]张量参数是D()
中的线性层。错误来自opt_D.step()
调用中的某个地方,然后在保留的图形上调用backward()
传递
发行说明中有以下克隆参数的示例:
def model(input, target, param):
return (input * param ** 2 - target).norm()
param = torch.randn(2, requires_grad=True)
input = torch.randn(2)
target = torch.randn(2)
sgd = optim.SGD([param], lr=0.001)
loss = model(input, target, param.clone())
loss.backward(retain_graph=True)
sgd.step()
loss.backward()
param.grad
这解决了这里的问题,但不是在初始示例中,因为参数来自鉴别器模型的线性层,所以有点细微差别