search

carpedm20 / ENAS-pytorch

PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"
Apache License 2.0
2.69k stars 492 forks source link

Why each activation function in each node has different id? #14

Open jinxin0924 opened 6 years ago

jinxin0924 commented 6 years ago

@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.