cnn_graph

cnn_graph copied to clipboard

Minor issue in "lib/utils.py".

1

I noticed line 139 in "lib/utils.py" should be modified from `model = gensim.models.Word2Vec(Sentences(self.documents), size)` to `model = gensim.models.Word2Vec(sentences=Sentences(self.documents), size=size)` I guess the parameter list of the Word2Vec constructor changed...

u42dani

Image Classification

2

I have an MNIST-like dataset for image classification using a Graph Convolutional Neural Network. Could you maybe suggest on how to make the adjacency matrix for such a dataset ?...

sayands

Reproducing mnist results on new image data ?

1

Hi, I am trying to reproduce the mnist results on images data of my own. They are simple parabolas (almost like the ones in the tutorial on jupyter notebook) and...

ahariri13

For some reason, I felt the need to clean up my stuff a bit. - [x] Merge dangling branches: `wikipedia` (4bf213d), `plot-filters` (49431c1), `long-standing` (742ff46). The code is left as...

mdeff

node signal is vector

5

I appreciate your implementation. In the introduction of usage, an example of data matrix X=[x1,...,xn]^T is used. xi is a vector containing signals on all nodes in the graph. The...

va1102

I have been trying to run `usage.ipynb` notebook. Even if I fix the error in #46 as described in #46 , the line `accuracy, loss, t_step = model.fit(X_train, y_train, X_val,...

ilteralp

Hi, I work on similar stuff and noticed that there is a bug in your code where you rearrange the matrix according to the indices. I am not sure if...

isukrit

Can I feed different graph for each data?

10

Thanks you for share this implementation. Suppose each data has different graph structure...(same node number but different edges and edge weights) In this case... can I feed different graph for...

hello072

node classification task

1

It seems that it's doing signal classification / regression in the notebook 'usage' . What change should I make to let it do node classification / regression? Only change the...

yeiamx

laplacian diagonal elements for fake nodes

4

Hello Michaël, My colleague told me when I use the `graph.laplacian` function, I have to assign 0.0 to the diagonal elements of the `L` matrix on the fake nodes. The...

maosi-chen