Allen

@lyu18 I encountered the same problem as you. And I looked into the code of original paper and found out that [they anneal the `epsilon_std`](https://github.com/HIPS/molecule-autoencoder/blob/master/autoencoder/variationaldense.py#L79). Maybe this can help the...

@lyu18 It helps to improve the reconstruction accuracy when training. This is expected since it is some kind of tradeoff between AE and VAE. But the KL divergence loss is...

Hi Weihua, How to preprocess Chem data to generate atom features and graph edge index? Could you please also provide that code? I have a new dataset and would like...

Thanks for your kind reply and help! My question is resolved.

Hi @skye95git, I do not have this problem. I guess it is related to your CUDA installation. You may find a similar issue [here](https://github.com/pyg-team/pytorch_geometric/issues/2040).

Thanks for your response! Do you refer to V2 dataset or V2 code? I still can not reproduce results with V1 code. I find the V1 code is easier to...

Thank you very much for your quick response! I used this script for the V1 code but can not reproduce the results. That is exactly my original question.

Yes, I am trying to train the Graphormer on PCQM4M-LSC from scratch. Thanks for the reminder! Since I have adapted the V1 for my own research, I prefer to use...

@SinDongHwan If you work in Linux, you can also increase the swap space.

@Yuli555 I have tried your method and it did not work. Have you tried it yourself?