torchgfn icon indicating copy to clipboard operation
torchgfn copied to clipboard

GFlowNet library

Results 42 torchgfn issues
Sort by recently updated
recently updated
newest added

Implement the molecules environment following the current API. More functions might be needed !

enhancement

https://cirun.io/ have a free Open Source plan for instance

Copied from https://github.com/saleml/torchgfn/pull/66 - Simplify the code. I don't think we need the BoxPFEstimator and BoxPFNeuralNet to be two distinct classes. It would be easier if all the logical existed...

https://pytorch.org/docs/stable/nested.html#module-torch.nested

We should take inspiration from these folks https://torchprotein.ai/ I can touch base to see how they built all of this stuff. Very pro.

`module.parameters()` will by default return both of these as a single list / dict, but it is common to give a unique learning rate to the `logZ` parameter (for example)....

As was done in https://github.com/saleml/torchgfn/pull/79 for the `master` branch: ``` def test_extend_trajectories_on_cuda(): import os import sys sys.path.insert(0, os.path.abspath("__file__" + "/../")) from src.gfn.containers.trajectories import Trajectories as Traj torch.manual_seed(0) env = HyperGrid(ndim=4,...