cauivy

请问大家解决问题了吗？

@speedinghzl Hello! I configured my conda-env with python3.7.1 and pytorch1.11. After complied according to https://github.com/speedinghzl/CCNet/tree/pytorch-1.1#requirements, I still got the error: from torch.utils.ffi import _wrap_function raise ImportError("torch.utils.ffi is deprecated. Please use...

> Hi, thanks for the great work and code. > > When I try to build the code, the build.sh is fine but when I run the build.py, an error...

> @cauivy You do not have to compile cc_attention if you are using the Pytorch-1.1 branch. @speedinghzl Thanks for your reply! I used Pythorch-1.1 branch and followed the README: #...

> @cauivy Is the error message is thrown out when you run the [script](https://github.com/speedinghzl/CCNet/tree/pytorch-1.1#training-and-evaluation)? > After checking my PyTorch, my Pytorch version is 1.2.0. But Pytorch 1.1 should be ok....

> > @cauivy Is the error message is thrown out when you run the [script](https://github.com/speedinghzl/CCNet/tree/pytorch-1.1#training-and-evaluation)? > > After checking my PyTorch, my Pytorch version is 1.2.0. But Pytorch 1.1 should...

> > @cauivy Is the error message is thrown out when you run the [script](https://github.com/speedinghzl/CCNet/tree/pytorch-1.1#training-and-evaluation)? > > After checking my PyTorch, my Pytorch version is 1.2.0. But Pytorch 1.1 should...

If your default CUDA is not 8.0, then change the path '/usr/local/cuda/include' in the build.sh into your cuda-8.0's path, e.g., '/usr/local/cuda-8.0/include'.

@tobyyouup Hi, tobyyouup, do you remember how long it took to train step 60k with batchsize 32 on iwslt14 de-en?

same problem occurred...