georgemilosh/Climate-Learning
How to predict extreme events in climate using rare event algorithms and modern tools of machine learning
Jupyter NotebookMIT
Issues
- 0
- 1
import params from external folder
#92 opened by AlessandroLovo - 0
- 1
- 0
Allow to enable and disable mods
#88 opened by AlessandroLovo - 1
Put some error message when the year_list exceeds the size of the file we load so that it is clear what is happening
#60 opened by georgemilosh - 0
cannot load kernels from composite in IIPR
#87 opened by AlessandroLovo - 1
'monitor' is ignored to compute the score
#86 opened by AlessandroLovo - 1
Support for cascading inheritance
#82 opened by AlessandroLovo - 0
`probabilistic_regression`: put the activation function for sigma in the model architecture rather than in the loss function
#85 opened by AlessandroLovo - 0
It is a bad idea to write to home directory commit #d1ba925cbddd69d00bd297c4cdfc90efc8a5f1f5
#76 opened by georgemilosh - 0
pass metrics from command line
#84 opened by AlessandroLovo - 1
- 0
`lsm2mask` should be handled better
#81 opened by AlessandroLovo - 6
CESM France mask could be better
#79 opened by AlessandroLovo - 0
- 1
`Learn2_new.py` trainer inheritence
#71 opened by georgemilosh - 11
Transfer Learning from outside folder fails
#74 opened by georgemilosh - 1
- 0
Write docstring for gaussian approx
#63 opened by AlessandroLovo - 1
Support for single fold run
#62 opened by AlessandroLovo - 2
xarray friendly `ef.create_mask`
#68 opened by AlessandroLovo - 1
Leap years
#69 opened by AlessandroLovo - 0
Queue file
#72 opened by AlessandroLovo - 0
- 8
the default behavior should be to load from a repository config file which documents where to look for the data
#65 opened by georgemilosh - 0
- 12
Reduce memory usage!
#50 opened by georgemilosh - 0
Reduce the size of the repository
#64 opened by georgemilosh - 3
transfer learning on `u`
#53 opened by georgemilosh - 5
Data not normalized prior to being fed into the model when computing Y_pred_unbiased?
#58 opened by georgemilosh - 1
Testing the network before loading data
#55 opened by georgemilosh - 0
- 5
- 2
seems that this condition is restrictive. I don't see a reason why we need to limit the majority class to never be smaller@georgemilosh
#52 opened by georgemilosh - 2
- 1
`field_infos` should be a json file
#47 opened by georgemilosh - 0
- 0
Working with CESM
#43 opened by georgemilosh - 1
- 2
`nfolds` is kwarg of both `prepare_XY` and `k_fold_cross_val` which can cause problems
#46 opened by georgemilosh - 1
Merge the subm2 and main
#39 opened by georgemilosh - 0
Make more readable and compact notebooks
#37 opened by AlessandroLovo - 0
Implement analog method in VAE
#36 opened by georgemilosh - 1
Better exploitation of xarray features
#31 opened by AlessandroLovo - 2
Use submodules
#34 opened by AlessandroLovo - 0
More information in README.md
#35 opened by AlessandroLovo - 0
Enable the possibility to run autoencoder on reduced space using main branch
#33 opened by georgemilosh - 1
Better masked average
#32 opened by AlessandroLovo - 1
More flexible choice of the data domain
#30 opened by AlessandroLovo