Ghouthi Boukli Hacene

I also have the same problem, did you resolved it?

Hello @unixpickle, First I would like to thank you for your excellent work that helps me a lot in my research. I would like to ask you if I can...

yes I obtained it several times

I just took resnet18 and compute a kmeans on its weight (independently on each layer)

yes this is exactly what I am trying to do

I used euclidean distance

Hello, I have the same issue. Can you please explain to me what did you do? Thank you

you can solve it as follows tmp = buf[start:start+num_w] tmp = tmp.view(conv_model.weight.shape) conv_model.weight.data.copy(tmp)

Can you share your code?

Hello, You are right concerning the difference between clone and copy . I tested the code on Pythorch 0.4 and 1