Jason Cheung comments

Repositories
Issues
Comments

Results 4 comments of


                                            Jason Cheung

the inference speed is much slower than original TensorFlow code

I met the same problem

Test accuracy on Cora, Citeseer, and Pubmed using original split

The accuracy on Pubmed is close to the report result (77.6)

Test accuracy on Cora, Citeseer, and Pubmed using original split

For cora, the new result is avg 81.4 +-0.5

datasets partition

@tkipf hi, tkipf. After running this Pytorch version GCN, the accuracy I get (~83% on cora) is much higher than the results(~81%) reported in your paper(Tensorflow version), and the load_data...