clean scripts
-
Review changes -
-
Download -
Patches
-
Plain diff
Il reste encore à ajouter plus de plots dans compute_results.py (pour l'instant il y a un exemple qui plot les loss sur train/dev/test).
Question : Dans le notebook il y a une version de la prédiction calculée avec une division de la somme des poids, et une version sans. C'était laquelle la bonne déjà ?
EDIT 1 - Exemple d'utilisation :
python code/train.py --dataset_name=california_housing --normalize_D --dataset_normalizer=standard --extracted_forest_size 10 20 30 --random_seed_number=2
python code/compute_results.py --experiment_ids 1Edited by Charly Lamothe
Merge request reports
Compare and
- version 24a0f7c96f
- version 233e8f934b
- version 229a9a3bff
- version 219830bbe0
- version 20211dc83a
- version 19cb0030d8
- version 187dd2aab5
- version 17708b1731
- version 168b3a6c49
- version 150fce0319
- version 147455fd98
- version 13d45cbb42
- version 12d89d9d52
- version 11d67e49c8
- version 10fc19c39e
- version 928b804c6
- version 89199d9bb
- version 7a5f920e0
- version 6306656fc
- version 5e0abe67e
- version 4a6a476ce
- version 3ec569ad5
- version 244e43b58
- version 15e990b2b
- master (base)
- latest versionce8de50259 commits,
- version 24a0f7c96f56 commits,
- version 233e8f934b46 commits,
- version 229a9a3bff43 commits,
- version 219830bbe042 commits,
- version 20211dc83a41 commits,
- version 19cb0030d839 commits,
- version 187dd2aab538 commits,
- version 17708b173137 commits,
- version 168b3a6c4936 commits,
- version 150fce031935 commits,
- version 147455fd9834 commits,
- version 13d45cbb4233 commits,
- version 12d89d9d5229 commits,
- version 11d67e49c828 commits,
- version 10fc19c39e27 commits,
- version 928b804c626 commits,
- version 89199d9bb25 commits,
- version 7a5f920e024 commits,
- version 6306656fc23 commits,
- version 5e0abe67e22 commits,
- version 4a6a476ce21 commits,
- version 3ec569ad520 commits,
- version 244e43b5819 commits,
- version 15e990b2b18 commits,
Compare changes
- Side-by-side
- Inline
Files
36Loading