Manan Goel

Hi @function2-llx ! Engineer from W&B here. The current design of the loggers in pytorch lightning for training on multiple processes is such that the main wandb run is accessible...

@rohitgr7 can this be closed?

Hi! Engineer from W&B here. In PL 1.7 this change of using the project as a default run name instead of random wandb run names (I love those too) was...

@awaelchli I think #14145 looks really cool and seems like a simple elegant solution. I'm testing it on my end. I think it is really great for the user experience!...

Hi @remivanbel ! Engineer from W&B here. I think adding a flatten option like this could possibly lead to some unexpected behaviour and might cause changes to other workflows because...

Also do pos1 and pos2 have to be the positions of the ligand after docking i.e. the docked pose?

The ```dgl``` version is ```0.5.3``` The ```dgllife``` version is ```0.2.6``` I tried using 4WTG instead and that also threw the same error.

Apologies. I gave the incorrect snippet. ``` from dgllife.model.model_zoo.acnn import ACNN import dgl from rdkit import Chem from rdkit.Chem import AllChem import torch from dgllife.utils import ACNN_graph_construction_and_featurization model = ACNN()...

4WTG is just something I picked randomly https://www.rcsb.org/structure/4WTG GitHub doesn't allow me to attach a PDB file

The last line of the code snippet ``` print(model(batch)) ``` ```batch``` is input to the ACNN model of which ```model``` is an instance