2D-VQ-AE-2 icon indicating copy to clipboard operation
2D-VQ-AE-2 copied to clipboard

2D Vector-Quantized Auto-Encoder for compression of Whole-Slide Images in Histopathology

Results 4 2D-VQ-AE-2 issues
Sort by recently updated
recently updated
newest added

Source: `2021-11-01/12-14-29/0/lightning_logs/version_8317429 ` ![ 2021-11-01/12-14-29/0/lightning_logs/version_8317429 ](https://user-images.githubusercontent.com/5969044/139838966-05ada298-c546-4b64-9258-0c78ba00f689.png)

Problem: - pl.seed_everything only seeds numpy.random, the new numpy.default_rng() is not seeded. - This leads to un-seeded crops, which are not desirable from a reproducibility perspective Solution: - Use pytorch.random

Pruners are not currently supported through the hydra optuna sweeper plugin: https://github.com/facebookresearch/hydra/issues/1710 . Adding the pruner to the sweeper ourselves might be doable, as it seems like a single argument...

- Nested sampling is supported in optuna: https://optuna.readthedocs.io/en/stable/tutorial/10_key_features/002_configurations.html - Nested sampling is not supported in hydra - Ideally we would like categorical choices to be config options, i.e. set choices...