使用pregrained vgg16模型的CUDNN错误
问题描述:
我想提取VGG16模型中最后一层的激活。为此,我在模型上使用了一个装饰器,如下所示。使用pregrained vgg16模型的CUDNN错误
当我将一个cuda张量传递给模型时,我得到一个CUDNN_STATUS_INTERNAL_ERROR和下面的回溯。
任何人都知道我错了哪里?
回溯:
File "/media/data1/iftachg/frame_glimpses/parse_files_to_vgg.py", line 80, in get_activation
return model(image)
File "/media/data1/iftachg/miniconda2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 206, in __call__
result = self.forward(*input, **kwargs)
File "/media/data1/iftachg/frame_glimpses/partial_vgg.py", line 24, in forward
x = self.vgg16.features(x)
File "/media/data1/iftachg/miniconda2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 206, in __call__
result = self.forward(*input, **kwargs)
File "/media/data1/iftachg/miniconda2/lib/python2.7/site-packages/torch/nn/modules/container.py", line 64, in forward
input = module(input)
File "/media/data1/iftachg/miniconda2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 206, in __call__
result = self.forward(*input, **kwargs)
File "/media/data1/iftachg/miniconda2/lib/python2.7/site-packages/torch/nn/modules/conv.py", line 237, in forward
self.padding, self.dilation, self.groups)
File "/media/data1/iftachg/miniconda2/lib/python2.7/site-packages/torch/nn/functional.py", line 39, in conv2d
return f(input, weight, bias)
RuntimeError: CUDNN_STATUS_INTERNAL_ERROR
类:
class partial_vgg(nn.Module):
def __init__(self):
super(partial_vgg, self).__init__()
self.vgg16 = models.vgg16(pretrained=True).cuda()
for param in self.vgg16.parameters():
param.requires_grad = False
def forward(self, x):
x = self.vgg16.features(x)
x = x.view(x.size(0), -1)
for l in list(self.vgg16.classifier.children())[:-3]:
x = l(x)
return x
答
显然cudnn错误是非常无益的,有一个与代码本身没有问题 - 这就是我试图在图形处理器访问已被使用。
答
这看起来像一个张力塑形错误。如上所述,CUDNN错误消息几乎是无用的。要获得更直观的错误消息,请在CPU上运行您的代码。
net.cpu()
不知道你的错误,但我认为可能有一个更简单的方法来做你想做的事情。看看我的答案,它解释了如何使用预训练模型并从中创建新模型/仅提取它的一部分以构建新模型:https://*.com/questions/44146655/how-to-convert -pretrained-FC-层到CONV层合pytorch/44410334#44410334 – mexmex