search

DeepGraphLearning / GearNet

GearNet and Geometric Pretraining Methods for Protein Structure Representation Learning, ICLR'2023 (https://arxiv.org/abs/2203.06125)
MIT License
253 stars 28 forks source link

About The Pre-training Process #9

Closed Mrz-zz closed 1 year ago

Mrz-zz commented 1 year ago

Hey, I am sorry to trouble you about the pre-training details about GeatNet. :)

After pre-training on the AlphaFold, will you fix the model's parameters and only change the prediction head's parameter? Or update the pre-trained model and its corresponding prediction head together?

Oxer11 commented 1 year ago

Hi! After pretraining, we finetune both the model and prediction head together. You can simply finetune the model with the same config file by passing the checkpoint in the argument.

Mrz-zz commented 1 year ago

Ok, I will try to fine-tune the model based on your suggestions. Best wishes!