carpedm20/ENAS-pytorch

Why each activation function in each node has different id?

jinxin0924 opened this issue · 0 comments

@dukebw Hi, thanks for your code. I have a detailed problem:
In your code, you build embedding :

        num_total_tokens = sum(self.num_tokens)

        self.encoder = torch.nn.Embedding(num_total_tokens,
                                          args.controller_hid)

This code shows that each previous node and activation function in different nodes have different ids. I am wondering about it. It would be great if you could help check this.