DanChen001

Hi @twtygqyy Sorry for the late reply. Thank you for helpful suggestions.

Hi, @twtygqyy I solved this problem as suggested https://github.com/twtygqyy/pytorch-vdsr/issues/11 @ZhaoJinHA Thanks. However, I do not know the reason, do you know why? thanks

for testing, I have the following problem, do you know why? Thanks. @twtygqyy ##################### => use gpu id: '0' C:\ProgramData\Anaconda3\lib\site-packages\torch\serialization.py:425: SourceChangeWarning: source code of class 'torch.nn.modules.container.Sequential' has changed. you can...

> Hi @DanChen001 , the problem is due to the python version. Please refer [#21 (comment)](https://github.com/twtygqyy/pytorch-vdsr/issues/21#issuecomment-372150250) for the solution. > And I think the first issue you mentioned is due...

Hi, did you guys solve this problem? I can train this network successfully. However, when i do testing, i have the same problem: Message type "caffe.LayerParameter" has no field named...

@farmingyard I can train this network successfully. However, when i do testing, i have the this problem: Message type "caffe.LayerParameter" has no field named "shuffle_channel_param". do you know how to...

@haoliyoupai09 can you use this code on Caffe + Matcaffe successfully?

> Yes, no error occurs during the compilation of matcaffe and running of code. But the performance is not good with deformable convolutional network. I do not know why. @haoliyoupai09...

> Yes, no error occurs during the compilation of matcaffe and running of code. But the performance is not good with deformable convolutional network. I do not know why. @haoliyoupai09...

@wk910930 @unsky I have the same question. Could you help me? Thanks