Veronika Thost
Veronika Thost
Thank you for providing this nice library! We have tried for quite some time to get the retrosynthesis example to work with a simple SMILES string but have failed terribly....
I am using a different dataset with larger molecules, however this breaks the code (e.g. the tree walker has too large data structures in `batch_make_att_masks`). I see `cmdargs.max_decode_steps` and would...
Did you filter the training data from https://cscdata.nrel.gov/#/datasets/ad5d2c9a-af0a-4d72-b943-1e433d5750d6 in a specific way? Because the smiles_train from there (which I assume you used?) contains a few more samples. Thank you already!
Hi, Thank you so much for sharing the code! I want to use it and am wondering if it is fair to generate the vocabulary based on all data. In...
Would it be possible for you to provide epoch_4_checkpoint.pth.tar via google or similar now? I know that there was an issue you closed in June 2018... It seems that the...
Hi, - The loss function you give in the paper differs from what the code does (it seems to me). I see that nn.MultiLabelMarginLoss is one part, but I do...
Thank you for providing all the code, it's a very interesting model! Have you by any chance insights into how Uni-Mol performs for molecular property prediction when it's pre-trained on...
Hi, Thank you providing the code and details about the data leakage. I just want to make sure I understand correctly: We can still use the old checkpoints but need...
SBU's `mapping_to_original_indices` contains items with values larger than `num_sites` in the pymatgen structure object given to create the MOF. Is this intended? I assumed these "original indices" to be the...
I try to build revision 34ea0d1dd6, because it still contains the json adjacency output. The problem is only with the python part (see below), but I need exactly that. Google...