dacapo.experiments
Subpackages
dacapo.experiments.architecturesdacapo.experiments.architectures.architecturedacapo.experiments.architectures.architecture_configdacapo.experiments.architectures.cnnectome_unetdacapo.experiments.architectures.cnnectome_unet_configdacapo.experiments.architectures.dummy_architecturedacapo.experiments.architectures.dummy_architecture_config
dacapo.experiments.arraytypesdacapo.experiments.arraytypes.annotationsdacapo.experiments.arraytypes.arraytypedacapo.experiments.arraytypes.binarydacapo.experiments.arraytypes.distancesdacapo.experiments.arraytypes.embeddingdacapo.experiments.arraytypes.intensitiesdacapo.experiments.arraytypes.maskdacapo.experiments.arraytypes.probabilities
dacapo.experiments.datasplitsdacapo.experiments.datasplits.datasetsdacapo.experiments.datasplits.datasets.arraysdacapo.experiments.datasplits.datasets.graphstoresdacapo.experiments.datasplits.datasets.datasetdacapo.experiments.datasplits.datasets.dataset_configdacapo.experiments.datasplits.datasets.dummy_datasetdacapo.experiments.datasplits.datasets.dummy_dataset_configdacapo.experiments.datasplits.datasets.raw_gt_datasetdacapo.experiments.datasplits.datasets.raw_gt_dataset_config
dacapo.experiments.datasplits.keysdacapo.experiments.datasplits.datasplitdacapo.experiments.datasplits.datasplit_configdacapo.experiments.datasplits.datasplit_generatordacapo.experiments.datasplits.dummy_datasplitdacapo.experiments.datasplits.dummy_datasplit_configdacapo.experiments.datasplits.train_validate_datasplitdacapo.experiments.datasplits.train_validate_datasplit_config
dacapo.experiments.startsdacapo.experiments.tasksdacapo.experiments.tasks.evaluatorsdacapo.experiments.tasks.evaluators.binary_segmentation_evaluation_scoresdacapo.experiments.tasks.evaluators.binary_segmentation_evaluatordacapo.experiments.tasks.evaluators.dummy_evaluation_scoresdacapo.experiments.tasks.evaluators.dummy_evaluatordacapo.experiments.tasks.evaluators.evaluation_scoresdacapo.experiments.tasks.evaluators.evaluatordacapo.experiments.tasks.evaluators.instance_evaluation_scoresdacapo.experiments.tasks.evaluators.instance_evaluator
dacapo.experiments.tasks.lossesdacapo.experiments.tasks.post_processorsdacapo.experiments.tasks.post_processors.argmax_post_processordacapo.experiments.tasks.post_processors.argmax_post_processor_parametersdacapo.experiments.tasks.post_processors.dummy_post_processordacapo.experiments.tasks.post_processors.dummy_post_processor_parametersdacapo.experiments.tasks.post_processors.post_processordacapo.experiments.tasks.post_processors.post_processor_parametersdacapo.experiments.tasks.post_processors.threshold_post_processordacapo.experiments.tasks.post_processors.threshold_post_processor_parametersdacapo.experiments.tasks.post_processors.watershed_post_processordacapo.experiments.tasks.post_processors.watershed_post_processor_parameters
dacapo.experiments.tasks.predictorsdacapo.experiments.tasks.predictors.affinities_predictordacapo.experiments.tasks.predictors.distance_predictordacapo.experiments.tasks.predictors.dummy_predictordacapo.experiments.tasks.predictors.hot_distance_predictordacapo.experiments.tasks.predictors.inner_distance_predictordacapo.experiments.tasks.predictors.one_hot_predictordacapo.experiments.tasks.predictors.predictor
dacapo.experiments.tasks.affinities_taskdacapo.experiments.tasks.affinities_task_configdacapo.experiments.tasks.distance_taskdacapo.experiments.tasks.distance_task_configdacapo.experiments.tasks.dummy_taskdacapo.experiments.tasks.dummy_task_configdacapo.experiments.tasks.hot_distance_taskdacapo.experiments.tasks.hot_distance_task_configdacapo.experiments.tasks.inner_distance_taskdacapo.experiments.tasks.inner_distance_task_configdacapo.experiments.tasks.one_hot_taskdacapo.experiments.tasks.one_hot_task_configdacapo.experiments.tasks.pretrained_taskdacapo.experiments.tasks.pretrained_task_configdacapo.experiments.tasks.taskdacapo.experiments.tasks.task_config
dacapo.experiments.trainersdacapo.experiments.trainers.gp_augmentsdacapo.experiments.trainers.gp_augments.augment_configdacapo.experiments.trainers.gp_augments.elastic_configdacapo.experiments.trainers.gp_augments.gamma_configdacapo.experiments.trainers.gp_augments.intensity_configdacapo.experiments.trainers.gp_augments.intensity_scale_shift_configdacapo.experiments.trainers.gp_augments.simple_config
dacapo.experiments.trainers.optimizersdacapo.experiments.trainers.dummy_trainerdacapo.experiments.trainers.dummy_trainer_configdacapo.experiments.trainers.gunpowder_trainerdacapo.experiments.trainers.gunpowder_trainer_configdacapo.experiments.trainers.trainerdacapo.experiments.trainers.trainer_config
Submodules
Package Contents
Classes
A trainable DaCapo model. Consists of an |
|
A class to represent a configuration of a run that helps to structure all the tasks, |
|
A class to represent the training iteration statistics. |
|
A class used to represent Training Statistics. |
|
A class used to represent the validation iteration scores in an organized structure. |
|
- class dacapo.experiments.Model(architecture: dacapo.experiments.architectures.architecture.Architecture, prediction_head: torch.nn.Module, eval_activation: torch.nn.Module | None = None)
A trainable DaCapo model. Consists of an
Architectureand a prediction head. Models are generated by ``Predictor``s.May include an optional eval_activation that is only executed when the model is in eval mode. This is particularly useful if you want to train with something like BCELossWithLogits, since you want to avoid applying softmax while training, but apply it during evaluation.
- num_out_channels: int
- num_in_channels: int
- forward(x)
- compute_output_shape(input_shape: funlib.geometry.Coordinate) Tuple[int, funlib.geometry.Coordinate]
Compute the spatial shape (i.e., not accounting for channels and batch dimensions) of this model, when fed a tensor of the given spatial shape as input.
- scale(voxel_size: funlib.geometry.Coordinate) funlib.geometry.Coordinate
- class dacapo.experiments.RunConfig
A class to represent a configuration of a run that helps to structure all the tasks, architecture, training, and datasplit configurations.
…
Attributes:
- task_config: TaskConfig
A config defining the Task to run that includes deciding the output of the model and different methods to achieve the goal.
- architecture_config: ArchitectureConfig
A config that defines the backbone architecture of the model. It impacts the model’s performance significantly.
- trainer_config: TrainerConfig
Defines how batches are generated and passed for training the model along with defining configurations like batch size, learning rate, number of cpu workers and snapshot logging.
- datasplit_config: DataSplitConfig
Configures the data available for the model during training or validation phases.
- name: str
A unique name for this run to distinguish it.
- repetition: int
The repetition number of this run.
- num_iterations: int
The total number of iterations to train for during this run.
- validation_interval: int
Specifies how often to perform validation during the run. It defaults to 1000.
- start_configOptional[StartConfig]
A starting point for continued training. It is optional and can be left out.
- task_config: dacapo.experiments.tasks.TaskConfig
- architecture_config: dacapo.experiments.architectures.ArchitectureConfig
- trainer_config: dacapo.experiments.trainers.TrainerConfig
- datasplit_config: dacapo.experiments.datasplits.DataSplitConfig
- name: str
- repetition: int
- num_iterations: int
- validation_interval: int
- start_config: dacapo.experiments.starts.StartConfig | None
- class dacapo.experiments.TrainingIterationStats
A class to represent the training iteration statistics.
- iteration
The iteration that produced these stats.
- Type:
int
- loss
The loss value of this iteration.
- Type:
float
- time
The time it took to process this iteration.
- Type:
float
- iteration: int
- loss: float
- time: float
- class dacapo.experiments.TrainingStats
A class used to represent Training Statistics.
- iteration_stats
List[TrainingIterationStats] an ordered list of training stats.
- add_iteration_stats(iteration_stats
TrainingIterationStats) -> None: Add a new set of iterations stats to the existing list of iteration stats.
- delete_after(iteration
int) -> None: Deletes training stats after a specified iteration number.
- trained_until() int
Gets the number of iterations that the model has been trained for.
- to_xarray() xr.DataArray
Converts the iteration statistics to a xarray data array.
- iteration_stats: List[dacapo.experiments.training_iteration_stats.TrainingIterationStats]
- add_iteration_stats(iteration_stats: dacapo.experiments.training_iteration_stats.TrainingIterationStats) None
Add a new iteration stats to the current iteration stats.
- Parameters:
iteration_stats (TrainingIterationStats) – a new iteration stats object.
- Raises:
assert – if the new iteration stats do not follow the order of existing iteration stats.
- delete_after(iteration: int) None
Deletes training stats after a specified iteration.
- Parameters:
iteration (int) – the iteration after which the stats are to be deleted.
- trained_until() int
The number of iterations trained for (the maximum iteration plus one). Returns zero if no iterations trained yet.
- Returns:
number of iterations that the model has been trained for.
- Return type:
int
- to_xarray() xarray.DataArray
Converts the iteration stats to a data array format easily manipulatable.
- Returns:
xarray DataArray of iteration losses.
- Return type:
xr.DataArray
- class dacapo.experiments.ValidationIterationScores
A class used to represent the validation iteration scores in an organized structure.
- iteration
The iteration associated with these validation scores.
- Type:
int
- scores
A list of scores per dataset, post processor
- Type:
List[List[List[float]]]
- parameters, and evaluation criterion.
- iteration: int
- scores: List[List[List[float]]]
- class dacapo.experiments.ValidationScores
- property criteria: List[str]
- property parameter_names: List[str]
- parameters: List[dacapo.experiments.tasks.post_processors.PostProcessorParameters]
- datasets: List[dacapo.experiments.datasplits.datasets.Dataset]
- evaluation_scores: dacapo.experiments.tasks.evaluators.EvaluationScores
- subscores(iteration_scores: List[dacapo.experiments.validation_iteration_scores.ValidationIterationScores]) ValidationScores
- add_iteration_scores(iteration_scores: dacapo.experiments.validation_iteration_scores.ValidationIterationScores) None
- validated_until() int
The number of iterations validated for (the maximum iteration plus one).
- compare(existing_iteration_scores: List[dacapo.experiments.validation_iteration_scores.ValidationIterationScores]) Tuple[bool, int]
Compares iteration stats provided from elsewhere to scores we have saved locally. Local scores take priority. If local scores are at a lower iteration than the existing ones, delete the existing ones and replace with local. If local iteration > existing iteration, just update existing scores with the last overhanging local scores.
- to_xarray() xarray.DataArray
- get_best(data: xarray.DataArray, dim: str) Tuple[xarray.DataArray, xarray.DataArray]
Compute the Best scores along dimension “dim” per criterion. Returns both the index associated with the best value, and the best value in two seperate arrays.