Closed Syzseisus closed 1 week ago
Sry for the confusion. We indeed use ogb==1.3.6
, the discrepancy between the ogb versions annoys me (the original moleculestm repo uses a very old version: 1.2.0).
So, one way to solve this:
ogb==1.3.6
xxxx/envs/ENV-NAME/lib/python3.9/site-packages/ogb/utils/features.py
and manually change the list of
'possible_chirality_list' : [
'CHI_UNSPECIFIED',
'CHI_TETRAHEDRAL_CW',
'CHI_TETRAHEDRAL_CCW',
'CHI_OTHER',
# 'misc' # just comment it
],
Thanks :)
Dear authors,
Thanks for the exciting work, but we have identified a potential inconsistency related to the OGB version specified in requirements.txt and the provided pre-trained weights.
Details:
requirements.txt
file specifiesogb==1.3.6
.ogb.graphpropropred.mol_encoder.AtomEncoder
, which utilizes theogb.utils.features.get_atom_feature_dims
function to createfull_atom_feature_dims
for generating theatom_embedding_list
ofAtomEncoder
.get_atom_feature_dims
function relies on theogb.utils.features.allowable_features
variable.ogb==1.3.5
,allowable_features["possible_chirality_list"]
includes the following four values ref:ogb==1.3.6
, an additional value, "misc", is included, making it five values ref.[4, 300]
, suggesting that they were generated usingogb==1.3.5
.AtomEncoder
is defined inogb==1.3.5
along therequirements.txt
, the shape of the weights become[5,300]
.requirements.txt
file is incorrect, or the checkpoint provided is based on an older version of OGB. (please refer to the attached picture below.)Request:
Could you please confirm and provide the correct information regarding the OGB version and the corresponding checkpoint? This clarification would greatly assist in ensuring the proper functioning of the model with the appropriate OGB version.
Thank you for your attention to this matter. Looking forward to your response.
Best regards,
Syzseisus
p.s. I'm really looking forward to the issue #1.