KKXR

I've just updated the default parameters. Now it should be fine to only specify the arguments with *require* mark.

May I ask the version of pytorch-lightning you are using? The API of pytorch-lightning is changing. In version 1.5.7 which is specified in the requirements.txt, the trainer has an argument...

Training data for QM9 is [here](https://github.com/THUNLP-MT/PS-VAE/tree/main/data/qm9), and checkpoints are provided [here](https://drive.google.com/drive/folders/1FeKZFJAM-mS_Rj4LD9biMTxKLmSVsG2V). "ckpts/{dataset}/{dataset}_guaca_dist/epoch{n}.ckpt" is used for guacamol distribution learning benchmark, where dataset can be qm9 or zinc250k. Similarly, the checkpoint in...

I just looked into the checkpoint directory and found what appeared to be the parameter settings as follows: python train.py \ --train_set ../data/qm9/train.txt \ --valid_set ../data/qm9/valid.txt \ --test_set ../data/qm9/test.txt \...

Hi, thanks for your interest in our work! I have updated the repo with the ability to process non-connected molecules on inference (commit 507c8f9 and 8c4b7b4). The basic logic is...

Hi, I think the following steps can help you train a model on a custom property. Suppose the property is GSK3B: 1. Implement get_gsk3b(molecule) in [src/evaluation/utils.py](https://github.com/THUNLP-MT/PS-VAE/blob/0dfcbd25b91e1127e556cb3c273260a41a1c3f35/src/evaluation/utils.py#L97). Here the argument molecule...

Hi, I think it might be because that pytorch 2.0.1 is used here. The base class of schedulers is _LRScheduler in versions below 2.0.0 (see [here](https://pytorch.org/docs/1.13/_modules/torch/optim/lr_scheduler.html#OneCycleLR)), which is used for...

Hi, I've updated procedure for installing the dependencies in the [README](https://github.com/THUNLP-MT/PS-VAE/blob/main/src/README.md#requirements). I apologize for the inconvenience caused by the previous buggy requirements.txt. As for the newly posted problem, I think...