plasma-python
plasma-python copied to clipboard
PPPLDeepLearning
PPPL deep learning disruption prediction package
- [ ] Establish actually useful regression and unit tests
Presently, at the end of every epoch, the trained weights are reloaded via a call to `Keras.Models.load_weights()` 3x separate times in order to evaluate the accuracy on the shots in...
Related to #58, #52, and #51. We should to add a continually-updated record of the `examples/second`, `second/batch`, and other statistics discussed in #51 to a new file `docs/Benchmarking.md` (or `ComputationalEfficiency.md`,...
Details reproduced from email correspondence in November 2019. There are slight discrepancies in the output of `guaranteed_preprocessed.py` from the current version of the code and the figures from Kates-Harbeck *et...
Following discussion on Wednesday 2019-12-04 in FRNN group meeting in San Diego, we need to start systematically saving the best trained models for: 1. Collaboration (no need for multiple users...
A tricky, undocumented step when switching to training on `jet_data_0D` is that the user must comment-out the line containing `'etemp_profile': etemp_profile, 'edens_profile': edens_profile,` in the definition of the dictionary that...
Straightforward alternative "single number" evaluation metric for ML algorithms--- should make comparisons to e.g. Rea *et al* (2019) and Churchill (2019) a bit easier. More generally, we could output various...
Example of the current per-step (iteration) diagnostic output provided by FRNN around epoch 22 of the D3D 0D model (run on 4 V100 GPUs of Traverse): ``` [0] step: 0...
Mostly repeating private email and in-person communication on this topic for reference notes and posterity. FRNN performance on V100s on the 2x IBM AC922 systems, OLCF Summit and Princeton's Traverse...
Metadata
Owner
Metadata
PPPL deep learning disruption prediction package