michelle-chou25

paddle.utils.run_check()就报这个错，但我的conda环境是全新的，什么都没有装，只有paddle，按照官网的要求装的cuda conda install paddlepaddle-gpu==2.4.1 cudatoolkit=11.2 -c https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/Paddle/ -c conda-forge

It doesn't work for me...

Dear Yuan, The file I run was src/demo.py, I also run the jupyter notbook demo and didn't have this issue. I debug the code, in self.proj(x), x.mlp_head.weight is in cuda,...

> Dear Yuan, > > The file I run was src/demo.py, I also run the jupyter notbook demo and didn't have this issue. I debug the code, in self.proj(x), x.mlp_head.weight...

> I failed to run the Jupiter script on my local machine, it said it can't find the path '/content/ast/', seems my IDE failed to connect to colab.

Thank you it solves the issue and may I know why? I also tried changing x to x.half(）， a different error msg as followed occurred: RuntimeError: Expected all tensors to...

> I think this again means your input and model are not in the same device. Which specific method solved your issue? Disable both imigenet_pretrained and audioset_pretrained

I tried it on another machine. it was not reproduced.

But changed line 132 in ast_models.py to self.mlp_head = nn.Sequential(nn.LayerNorm(self.original_embedding_dim), nn.Linear(self.original_embedding_dim, label_dim)).to("cuda") and line 18 in demo.py to test_input = torch.rand([10, input_tdim, 128]).to("cuda").half()

> But changed line 132 in ast_models.py to self.mlp_head = nn.Sequential(nn.LayerNorm(self.original_embedding_dim), nn.Linear(self.original_embedding_dim, label_dim)).to("cuda") and line 18 in demo.py to test_input = torch.rand([10, input_tdim, 128]).to("cuda").half() In the previous machine, the error...