hyperparameters_callback
Callback saving CAREamics configuration as hyperparameters in the model.
HyperParametersCallback
#
Bases: Callback
Callback allowing saving CAREamics configuration as hyperparameters in the model.
This allows saving the configuration as dictionary in the checkpoints, and loading it subsequently in a CAREamist instance.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
config | Configuration | CAREamics configuration to be saved as hyperparameter in the model. | required |
Attributes:
Name | Type | Description |
---|---|---|
config | Configuration | CAREamics configuration to be saved as hyperparameter in the model. |
Source code in src/careamics/lightning/callbacks/hyperparameters_callback.py
__init__(config)
#
Constructor.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
config | Configuration | CAREamics configuration to be saved as hyperparameter in the model. | required |
Source code in src/careamics/lightning/callbacks/hyperparameters_callback.py
on_train_start(trainer, pl_module)
#
Update the hyperparameters of the model with the configuration on train start.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
trainer | Trainer | PyTorch Lightning trainer, unused. | required |
pl_module | LightningModule | PyTorch Lightning module. | required |