我正在CUDA GPU上训练CNN，该CNN将3D医学图像作为输入并输出分类器。我怀疑pytorch中可能有错误。我正在运行pytorch 1.4.0。 GPU是'Tesla P100-PCIE-16GB'。在CUDA上运行模型时，出现错误
Traceback (most recent call last):
File "/home/ub/miniconda3/lib/python3.7/site-packages/IPython/core/interactiveshell.py", line 3331, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-55-cc0dd3d9cbb7>", line 1, in <module>
net(cc)
File "/home/ub/miniconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in __call__
result = self.forward(*input, **kwargs)
File "<ipython-input-2-19e11966d1cd>", line 181, in forward
out = self.layer1(x)
File "/home/ub/miniconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in __call__
result = self.forward(*input, **kwargs)
File "/home/ub/miniconda3/lib/python3.7/site-packages/torch/nn/modules/container.py", line 100, in forward
input = module(input)
File "/home/ub/miniconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in __call__
result = self.forward(*input, **kwargs)
File "/home/ub/miniconda3/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 480, in forward
self.padding, self.dilation, self.groups)
RuntimeError: Could not run 'aten::slow_conv3d_forward' with arguments from the 'CUDATensorId' backend. 'aten::slow_conv3d_forward' is only available for these backends: [CPUTensorId, VariableTensorId].
要复制该问题：
#input is a 64,64,64 3d image batch with 2 channels
class ConvNet(nn.Module):
def __init__(self):
super(ConvNet, self).__init__()
self.layer1 = nn.Sequential(
nn.Conv3d(2, 32, kernel_size=5, stride=1, padding=2),
nn.ReLU(),
nn.MaxPool3d(kernel_size=2, stride=2))
self.layer2 = nn.Sequential(
nn.Conv3d(32, 64, kernel_size=5, stride=1, padding=2),
nn.ReLU(),
nn.MaxPool3d(kernel_size=2, stride=2))
self.drop_out = nn.Dropout()
self.fc1 = nn.Linear(16 * 16*16 * 64, 1000)
self.fc2 = nn.Linear(1000, 2)
# self.softmax = nn.LogSoftmax(dim=1)
def forward(self, x):
# print(out.shape)
out = self.layer1(x)
# print(out.shape)
out = self.layer2(out)
# print(out.shape)
out = out.reshape(out.size(0), -1)
# print(out.shape)
out = self.drop_out(out)
# print(out.shape)
out = self.fc1(out)
# print(out.shape)
out = self.fc2(out)
# out = self.softmax(out)
# print(out.shape)
return out
net = Convnet()
input = torch.randn(16, 2, 64, 64, 64)
net(input)
答案 0 :(得分：7)
最初，我以为错误消息表明'aten::slow_conv3d_forward'尚未使用GPU（CUDA）实现。但是在查看了您的网络后，对我来说这没有意义，因为Conv3D是一个非常基本的操作，Pytorch团队应该在CUDA中实现这一点。
然后，我深入研究了源代码，发现输入不是CUDA张量，这会导致问题。
这是一个工作示例：
import torch
from torch import nn
#input is a 64,64,64 3d image batch with 2 channels
class ConvNet(nn.Module):
def __init__(self):
super(ConvNet, self).__init__()
self.layer1 = nn.Sequential(
nn.Conv3d(2, 32, kernel_size=5, stride=1, padding=2),
nn.ReLU(),
nn.MaxPool3d(kernel_size=2, stride=2))
self.layer2 = nn.Sequential(
nn.Conv3d(32, 64, kernel_size=5, stride=1, padding=2),
nn.ReLU(),
nn.MaxPool3d(kernel_size=2, stride=2))
self.drop_out = nn.Dropout()
self.fc1 = nn.Linear(16 * 16*16 * 64, 1000)
self.fc2 = nn.Linear(1000, 2)
# self.softmax = nn.LogSoftmax(dim=1)
def forward(self, x):
# print(out.shape)
out = self.layer1(x)
# print(out.shape)
out = self.layer2(out)
# print(out.shape)
out = out.reshape(out.size(0), -1)
# print(out.shape)
out = self.drop_out(out)
# print(out.shape)
out = self.fc1(out)
# print(out.shape)
out = self.fc2(out)
# out = self.softmax(out)
# print(out.shape)
return out
net = ConvNet()
input = torch.randn(16, 2, 64, 64, 64)
net.cuda()
input = input.cuda() # IMPORTANT to reassign your tensor
net(input)
请记住，当您将模型从CPU放置到GPU时，可以直接调用.cuda()，但是如果您将张量从CPU放置到GPU，则需要重新分配它，例如tensor = tensor.cuda()，而不是仅调用tensor.cuda()。希望有帮助。
输出：
tensor([[-0.1588, 0.0680],
[ 0.1514, 0.2078],
[-0.2272, -0.2835],
[-0.1105, 0.0585],
[-0.2300, 0.2517],
[-0.2497, -0.1019],
[ 0.1357, -0.0475],
[-0.0341, -0.3267],
[-0.0207, -0.0451],
[-0.4821, -0.0107],
[-0.1779, 0.1247],
[ 0.1281, 0.1830],
[-0.0595, -0.1259],
[-0.0545, 0.1838],
[-0.0033, -0.1353],
[ 0.0098, -0.0957]], device='cuda:0', grad_fn=<AddmmBackward>)