Configuration
The configuration summarizes all the parameters used internally by CAREamics. It is used to create a CAREamist
instance and is saved together with the checkpoints and saved models.
It is composed of four members:
Anatomy of the configuration
from careamics import Configuration
config_as_dict = {
"experiment_name": "my_experiment", # (1)!
"algorithm_config": { # (2)!
"algorithm_type": "fcn",
"algorithm": "n2v",
"loss": "n2v",
"model": { # (3)!
"architecture": "UNet",
},
},
"data_config": { # (4)!
"data_type": "array",
"patch_size": [128, 128],
"axes": "YX",
},
"training_config": {
"num_epochs": 1,
},
}
config = Configuration(**config_as_dict) # (5)!
- The name of the experiment, used to differentiate trained models.
- Configuration specific to the model.
- Configuration related to the data.
- Training parameters.
- The configuration is an object!
If the number of parameters looks too limited, it is because the configuration is hiding a lot of default values! But don't be afraid, we have designed convenience functions to help you create a configuration for each of the algorithm CAREamics offers.
In the next sections, you can dive deeper on how to use CAREamics configuration with different levels of expertise.
- (beginner) Convenience functions
- (beginner) Save and load configurations
- (intermediate) Build the configuration from scratch
- (intermediate) Full specification
- (intermediate) Algorithm requirements
- (advanced) Advanced configuration
- (all) Understanding the errors