search

longcw / pytorch2caffe

Convert PyTorch model to Caffemodel
541 stars 151 forks source link

KeyError: 'MkldnnConvolutionBackward' #25

Open maliho0803 opened 5 years ago

maliho0803 commented 5 years ago

hi, I just run your code, appeared this problem. what is wrong with the code?

dzyjjpy commented 5 years ago

what's your version for pytorch?

maliho0803 commented 5 years ago

'1.0.0.dev20190409'

在 2019年4月11日，下午12:09，jpy.cas notifications@github.com 写道：

what's your version for pytorch?

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/longcw/pytorch2caffe/issues/25#issuecomment-481957579, or mute the thread https://github.com/notifications/unsubscribe-auth/AOVptJs2KjHdJOxutM00gOQCVJF-Q1z_ks5vfrVfgaJpZM4cmcUU.

dzyjjpy commented 5 years ago

met similar issue when using 1.0.0. pls use torch 0.2.0 to have a try

791188299 commented 5 years ago

@maliho0803 Has the problem been solved? Can you share your method? Thank you very much.

you-old commented 5 years ago

？？

jianfeifeng commented 5 years ago

I also met this problem when i try to convert inception_v3 from pytorch to caffe.Has anyone solved this problem already? would you like to share the solution with us ? Thank you !

joehishi commented 5 years ago

sudo pip2 install http://download.pytorch.org/whl/cu80/torch-0.2.0.post3-cp27-cp27mu-manylinux1_x86_64.whl sudo pip2 install torchvision==0.1.8

twirlined commented 5 years ago

Met the same problem while trying to convert pytorch to caffe with pytorch 1.1.0 and torchvision 0.3.0. Does changing pytorch and torchvision version solve this problem? Thank you.

arya-none commented 4 years ago

when use 0.2.0, there's a new error: output_var = model(input_var) File "/usr/local/python3.7.5/lib/python3.7/site-packages/torch/nn/modules/module.py", line 224, in call result = self.forward(*input, *kwargs) File "/usr/local/python3.7.5/lib/python3.7/site-packages/torchvision/models/resnet.py", line 139, in forward x = self.conv1(x) File "/usr/local/python3.7.5/lib/python3.7/site-packages/torch/nn/modules/module.py", line 224, in call result = self.forward(input, **kwargs) File "/usr/local/python3.7.5/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 254, in forward self.padding, self.dilation, self.groups) File "/usr/local/python3.7.5/lib/python3.7/site-packages/torch/nn/functional.py", line 52, in conv2d return f(input, weight, bias) TypeError: argument 0 is not a Variable