Pytorch RuntimeError: Expected tensor for argument #1 ‘indices’ to have scalar type Long; but got CUDAType instead

I would suggest you to check the input type
I had the same issue which solved by converting the input type from int32 to int64.(running on win10)
ex:

x = torch.tensor(train).to(torch.int64)

Leave a Comment

Hata!: SQLSTATE[HY000] [1045] Access denied for user 'divattrend_liink'@'localhost' (using password: YES)