You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I wish to finetune Gearnet (distance prediction) for some other downstream tasks.
Now I have all atom positions and residue type and atom type. I used the same operation as fold3d to get protein. However, I do not know how can I get input (Tensor) – input node representations. I could not understand how those APIs passed this input into GearNet.
Yours Sincerely,
Jiale Zhao
The text was updated successfully, but these errors were encountered:
To use GearNet on your customized dataste, you can follow this tutorial, which describes how to use TorchDrug to construct data.Protein object and pass it into GearNet. Also, you can see this tutorial to learn about how to use pre-trained checkpoints.
Feel free to ask me if there are any other questions.
Dear Sir/Madam,
Thank you for your fantastic paper GearNet.
I wish to finetune Gearnet (distance prediction) for some other downstream tasks.
Now I have all atom positions and residue type and atom type. I used the same operation as fold3d to get protein. However, I do not know how can I get input (Tensor) – input node representations. I could not understand how those APIs passed this input into GearNet.
Yours Sincerely,
Jiale Zhao
The text was updated successfully, but these errors were encountered: