GraphNormalization icon indicating copy to clipboard operation
GraphNormalization copied to clipboard

num_features

Open SuperAttitude opened this issue 4 years ago • 3 comments

Hello, thank you very much for your work. I noticed num_features in your code. I want to know what it means and how it is set in use.Thank you for your reply.

SuperAttitude avatar Jun 23 '21 13:06 SuperAttitude

Hi, thanks for attention, 'num_features' means the number of node/edge feature channel in this work. and you can see more about 'num_features' in BatchNorm, InstanceNorm:

https://pytorch.org/docs/stable/generated/torch.nn.BatchNorm1d.html https://pytorch.org/docs/stable/generated/torch.nn.InstanceNorm1d.html#torch.nn.InstanceNorm1d

cyh1112 avatar Jun 23 '21 14:06 cyh1112

You can modify it in config file, such as 'configs/SBMs_node_clustering_GCN_CLUSTER_100k.json' line 27: net_params.hidden_dim

cyh1112 avatar Jun 24 '21 01:06 cyh1112

Thank you for your reply. I'll read it

SuperAttitude avatar Jun 24 '21 01:06 SuperAttitude