GPLaSDI

GPLaSDI copied to clipboard

dreamer2368

- `fd` module provides high-order, summation-by-parts finite-difference operators. - This is proven to approximate time derivative better. - `sindy.compute_sindy_data` is replaced with `sindy.compute_time_derivative` - `compute_time_derivative` returns the time-derivative array with...

dreamer2368

Incompatibility with up-to-date pytorch and numpy

1

This issue corresponds to the legacy code. The work-in-progress python package has already applied the fix for this issue. The legacy code currently solves SINDY using the outdated torch/numpy routines...

dreamer2368

This PR must be merged after PR #9 . Using [DistributedDataParallel](https://pytorch.org/docs/stable/generated/torch.nn.parallel.DistributedDataParallel.html#torch.nn.parallel.DistributedDataParallel) for data parallelism requires access to encoder and decoder as a `torch.nn.Module`. Current `Autoencoder` class provide `encoder` and `decoder`...

dreamer2368

# Restart capability The workflow now supports restart capability, saving/loading necessary data to/from a restart file. - Following classes support `export` and `load` function, which saves/loads from a dictionary: -...

dreamer2368