2017-09-24 44 views
0

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 

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 
+2

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://stackoverflow.com/questions/44146655/how-to-convert -pretrained-FC-层到CONV层合pytorch/44410334#44410334 – mexmex

回答

1

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。

1

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()