Open ShileiCao opened 3 months ago
You can find pseudo-code in https://github.com/google-research/neuralgcm/tree/8cffd3f1da4191c4507e97a1510fe468b7d97ada/neuralgcm/reference_code. We haven't released the full code mostly because the implementation is quite messy and entangled with internal Google tools, but we do plan/hope to release for training in the future, for our next generation models.
Is the full code for the training of the NeuralGCM provided? If so, how can we use it? Is it possible to re-train another NeuralGCM utilizing a subset of the variables mentioned? Thanks for your work.