Thomas Kipf
Thomas Kipf
This can be due to class imbalance when measuring accuracy. On Thu 25. Jul 2019 at 21:16 Saed Rezayi wrote: > Nope, I couldn't figure out why sometimes train_acc is...
For model saving/loading, `tf.train.Saver` should work: https://www.tensorflow.org/guide/saved_model You can get embeddings from a trained model via `model.z_mean` or `model.embeddings` (the latter one is a sample from a Gaussian latent variable...
Maybe this is a keras version issue. Can you try with v. 1.0.9?
Thanks - it could be that 2.2.0 is not working due to some change in the API. Can you try v.1.0.9?
Interesting, maybe the new keras version doesn't need the sparsity argument anymore for sparse inputs. Glad you could figure it out. Let's leave this issue open so others can find...
For batch-wise training with multiple graphs, please have a look here: https://github.com/tkipf/gcn/issues/4 On Thu 4. Jun 2020 at 09:42 Monica Tare wrote: > Hi, > > I have a dataset...
Have a look here: https://github.com/tkipf/gcn/issues/4. This only applies for the TensorFlow implementation though. Hope this helps! On Wed 27. Jun 2018 at 23:42 gailmargolis76 wrote: > My input is such...
Ah, i just realized you’re explicitly asking about how to do this in keras. This is a bit tricky due to the restrictions of the API and I would recommend...
I think the Theano backend is broken. You might want to test this with a TensorFlow backend?
Thanks for the pull request. I would like to keep the default split sizes as they are, as this more closely matches the dataset splits from our paper, but I...