After T.ToUndirected, the data.is_undirected() is still False

[PolarisRisingWar]

This is my code (in which data is a HeteroData object):

print(data.is_undirected())
data=T.ToUndirected()(data)
print(data.is_undirected())

And the output is:

False
False

I think there must have some problems...

[rusty1s]

I think this is already fixed on lastest master/nightly. Can you try to install latest PyG to see if that is indeed the case? Let me know!

[PolarisRisingWar]

This is my action list:

1. I've used conda install, so at first I used 'conda uninstall pyg`
2. My torch is 1.11.0, cudatoolkit is 10.2, so pip install torch-scatter -f https://data.pyg.org/whl/torch-1.11.0+cu102.html pip install torch-sparse -f https://data.pyg.org/whl/torch-1.11.0+cu102.html pip install pyg-nightly

Then I found it works! The output now is

False
True

[rusty1s]

Super. I will craft a new PyG release with this changes soon.