| { | |
| "model_class": "physioex.models.chambon2018:Chambon2018Net", | |
| "model_kwargs": { | |
| "n_classes": 5, | |
| "in_channels": 1, | |
| "sf": 128, | |
| "n_times": 3840, | |
| "dropout": 0.25 | |
| }, | |
| "training": { | |
| "dataset": "mass", | |
| "dataset_kwargs": { | |
| "cohort": 3 | |
| }, | |
| "channels": [ | |
| "EEG" | |
| ], | |
| "pipeline_preset": "raw", | |
| "pipeline_kwargs": { | |
| "target_fs": 128.0 | |
| }, | |
| "sequence_length": 3, | |
| "max_epochs": 100, | |
| "lr": 0.001, | |
| "weight_decay": 0, | |
| "batch_size": 128, | |
| "loss": "CrossEntropyLoss", | |
| "fold": 0, | |
| "early_stopping_patience": 5 | |
| }, | |
| "reference": "Chambon et al. 2018 - A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series (arXiv:1707.03321)" | |
| } |