Python 如何修复PyTorch中预期的CUDA got CPU错误?
我一直在努力寻找代码中的错误。我正在尝试实现DCGAN文件,在过去的两天里,我经历了这些错误。谁能帮我修一下吗 我用GPU运行时在GoogleColab上训练这个,但是我得到了这个错误。昨天,我实现了由Ian Goodfello编写的第一篇GAN论文,我没有发现这个错误。我不知道发生了什么事,如果有任何帮助,我们将不胜感激。此外,请检查发电机输入是否正确 我已经问了这个问题,没有人回复以前的帖子。一个人回答了这个问题,但他所说的只是上下改变线条,这也会产生同样的错误。请帮帮我 代码如下:Python 如何修复PyTorch中预期的CUDA got CPU错误?,python,pytorch,generative-adversarial-network,dcgan,Python,Pytorch,Generative Adversarial Network,Dcgan,我一直在努力寻找代码中的错误。我正在尝试实现DCGAN文件,在过去的两天里,我经历了这些错误。谁能帮我修一下吗 我用GPU运行时在GoogleColab上训练这个,但是我得到了这个错误。昨天,我实现了由Ian Goodfello编写的第一篇GAN论文,我没有发现这个错误。我不知道发生了什么事,如果有任何帮助,我们将不胜感激。此外,请检查发电机输入是否正确 我已经问了这个问题,没有人回复以前的帖子。一个人回答了这个问题,但他所说的只是上下改变线条,这也会产生同样的错误。请帮帮我 代码如下: imp
import torch
import numpy as np
import torch.nn as nn
import torch.nn.functional as F
import torchvision
import torchvision.transforms as transforms
from torchvision.utils import save_image
import torch.optim as optim
lr = 0.00002 #learning rate
nc = 3 #color channels
nz = 100 #size of latent vector or size of generator input
ngf = 64 #size of feature maps in generator
ndf = 64 #size of feature maps in discriminator
height = 128 #height of the image
width = 128 #width of the image
num_epochs = 5 #the variable name tells everything
workers = 2 #number of workers to load the data in batches
batch_size = 64 #batch size
image_size = 128 #resizing parameter
root = './simpsons/' #path to the training directory
beta1 = 0.5
img_shape = (nc, height, width)
class Generator(nn.Module):
def __init__(self):
super(Generator, self).__init__()
self.convt1 = nn.ConvTranspose2d(in_channels = nz, out_channels = ngf*8, kernel_size = 4, stride = 1, padding = 0, bias = False)
self.convt2 = nn.ConvTranspose2d(in_channels = ngf*8, out_channels = ngf*4, kernel_size = 4, stride = 2, padding = 1, bias = False)
self.convt3 = nn.ConvTranspose2d(in_channels = ngf*4, out_channels = ngf*2, kernel_size = 4, stride = 2, padding = 1, bias = False)
self.convt4 = nn.ConvTranspose2d(in_channels = ngf*2, out_channels = ngf, kernel_size = 4, stride = 2, padding = 1, bias = False)
self.convt5 = nn.ConvTranspose2d(in_channels = ngf, out_channels = 3, kernel_size=4, stride = 2, padding = 1, bias = False)
def forward(self, t):
t = self.convt1(t)
t = nn.BatchNorm2d(t)
t = F.relu(t)
t = self.convt2(t)
t = nn.BatchNorm2d(t)
t = F.relu(t)
t = self.convt3(t)
t = nn.BatchNorm2d(t)
t = F.relu(t)
t = self.convt4(t)
t = nn.BatchNorm2d(t)
t = F.relu(t)
t = self.convt5(t)
t = F.tanh(t)
return t
class Discriminator(nn.Module):
def __init__(self):
super(Discriminator, self).__init__()
self.conv1 = nn.Conv2d(in_channels = 3, out_channels = ndf, kernel_size = 4, stride = 2, padding = 1, bias = False)
self.conv2 = nn.Conv2d(in_channels = ndf, out_channels = ndf*2, kernel_size = 4, stride = 2, padding = 1, bias = False)
self.conv3 = nn.Conv2d(in_channels = ndf*2, out_channels = ndf*4, kernel_size = 4, stride = 2, padding = 1, bias = False)
self.conv4 = nn.Conv2d(in_channels = ndf*4, out_channels = ndf*8, kernel_size = 4, stride = 2, padding = 1, bias = False)
self.conv5 = nn.Conv2d(in_channels = ndf*8, out_channels = 1, kernel_size = 4, stride = 1, padding = 0, bias = False)
def forward(self, t):
t = self.conv1(t)
t = F.leaky_relu(t, 0.2)
t = self.conv2(t)
t = nn.BatchNorm2d(t)
t = F.leaky_relu(t, 0.2)
t = self.conv3(t)
t = nn.BatchNorm2d(t)
t = F.leaky_relu(t, 0.2)
t = self.conv4(t)
t = nn.BatchNorm2d(t)
t = F.leaky_relu(t, 0.2)
t = self.conv5(t)
t = F.sigmoid(t)
return t
def weights_init(m):
classname = m.__class__.__name__ #returns the class name(eg: Conv2d or ConvTranspose2d)
if classname.find('Conv') != -1:
nn.init.normal_(m.weight.data, 0.0, 0.02) #0.0 is mean and 0.02 is standard deviation
elif classname.find('BatchNorm') != -1:
nn.init.normal_(m.weight.data, 1, 0.02) #1 is mean and 0.02 is standard deviation
nn.init.constant_(m.bias.data, 0.0)
def load_data(image_size, root):
transform = transforms.Compose([
transforms.Resize(image_size),
transforms.ToTensor(),
transforms.Normalize((0.486, 0.486, 0.486), (0.486, 0.486, 0.486))
])
train_set = torchvision.datasets.ImageFolder(root = root, transform = transform)
return train_set
#getting the batches of data
train_set = load_data(image_size, root)
dataloader = torch.utils.data.DataLoader(train_set, batch_size = batch_size, shuffle = True, num_workers = workers)
generator = Generator()
discriminator = Discriminator()
generator.apply(weights_init)
discriminator.apply(weights_init)
print(generator)
print(discriminator)
criterion = nn.BCELoss()
noise = torch.randn(64, nz, 1, 1)
optimizer_G = optim.Adam(generator.parameters(), lr = lr, betas=(beta1, 0.999))
optimizer_D = optim.Adam(discriminator.parameters(), lr = lr, betas=(beta1, 0.999))
if torch.cuda.is_available():
print("CUDA available")
generator = generator.to('cuda')
discriminator = discriminator.to('cuda')
criterion = criterion.cuda('cuda')
Tensor = torch.cuda.FloatTensor
print("Networks moved on to cuda")
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(dataloader):
val = Tensor(images.size(0), 1).fill_(1.0)
fake = Tensor(images.size(0),1).fill_(0.0)
real_images = images
optimizer_G.zero_grad()
gen_input = Tensor(np.random.normal(0,1,(512,100,4,4)))
gen = generator(gen_input)
g_loss = loss_func(discriminator(gen), val)
g_loss.backward()
optimizer_G.step()
optimizer_D.zero_grad()
real_loss = loss_func(discriminator(real_images), val)
fake_loss = loss_func(discriminator(gen.detach()),fake)
d_loss = (real_loss + fake_loss)/2
d_loss.backward()
optimizer_D.step()
if i%900 == 0:
print("[EPOCH %d/%d] [Batch %d/%d] [D loss: %f] [G loss: %f]"%(epoch, num_epochs, i, len(dataset), d_loss.item(), g_loss.item()))
total_batch = epoch * len(dataset) + i
if total_batch%400 == 0:
save_image(gen.data[:25], 'output/%d.png' % total_batch, nrow=5)
下面是错误:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-36-0af32f223344> in <module>()
18 gen_input = gen_input.cuda()
19 #we then pass it to generator()
---> 20 gen = generator(gen_input) #this returns a image
21
22 #now calculate the loss wrt to discriminator output
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/batchnorm.py in __init__(self, num_features, eps, momentum, affine, track_running_stats)
40 self.track_running_stats = track_running_stats
41 if self.affine:
---> 42 self.weight = Parameter(torch.Tensor(num_features))
43 self.bias = Parameter(torch.Tensor(num_features))
44 else:
TypeError: expected CPU (got CUDA)
---------------------------------------------------------------------------
TypeError回溯(最近一次调用上次)
在()
18 gen_input=gen_input.cuda()
19#然后我们将其传递给生成器()
--->20 gen=生成器(gen_输入)#返回图像
21
22#现在计算鉴别器输出的损耗wrt
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/batchnorm.py in_uuuuuuinit_uuuuuu(self、num_u功能、eps、动量、仿射、轨迹、跑步统计)
40 self.track\u running\u stats=track\u running\u stats
41如果自仿射:
--->42自重=参数(火炬张量(num_特征))
43 self.bias=参数(火炬张量(num_特征))
44.其他:
TypeError:预期的CPU(获得CUDA)
任何帮助都将不胜感激。谢谢大家! 您使用的方式不正确。BatchNorm是一个层,就像Conv2d一样。它具有内部参数和缓冲区。
因此,您必须在生成器/鉴别器的
\uuuu init\uuuuu
中定义这些层。现在,您在
转发过程中定义层-这在很多方面都是错误的…因此,我需要创建self.bn1=nn.BatchNorm2d(num\u features=ngf*8)
对吗?@jaychandra是的。您需要为所有层定义self.bn1
等等。然后在forward
函数中,您需要调用t=self.bn1(t)
@jaychandra,您应该在移动到cuda后创建优化器。为什么你不使用移动张量(和模型)到cuda或CPU?非常感谢!我现在刚用过.to(设备)。现在修好了!我得到了另一个错误,它指出,期望4维权重[100128,4,4]的4维输入,但得到了大小为[64100]的2维输入
训练图像大小为128*200(h,w)。你也能帮我做这个吗。这是这本书