search

tkipf / keras-gcn

Keras implementation of Graph Convolutional Networks
MIT License
791 stars 266 forks source link

Why does it increased in dimension after every layer? #67

Open jessutanto opened 2 years ago

jessutanto commented 2 years ago

Hi, I'm just wondering why does it increase in dimension every time I add a GCN layer? Because it won't work when I put a BatchNormalization after a GCN layer.

image

image

This is the error I get when I put a BatchNorm in between the GCN layers:

ValueError: Input 0 of layer batch_normalization is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: [None, 10]

any help and explanation would be very appreciated. Thank you!