careamics 0.1.0rc2__py3-none-any.whl → 0.1.0rc4__py3-none-any.whl

careamics/config/callback_model.py

@@ -0,0 +1,92 @@
+"""Checkpoint saving configuration."""
+from __future__ import annotations
+
+from datetime import timedelta
+from typing import Literal, Optional
+
+from pydantic import (
+    BaseModel,
+    ConfigDict,
+    Field,
+)
+
+
+class CheckpointModel(BaseModel):
+    """_summary_.
+
+    Parameters
+    ----------
+    BaseModel : _type_
+        _description_
+    """
+
+    model_config = ConfigDict(
+        validate_assignment=True,
+    )
+
+    monitor: Literal["val_loss"] = Field(default="val_loss", validate_default=True)
+    verbose: bool = Field(default=False, validate_default=True)
+    save_weights_only: bool = Field(default=False, validate_default=True)
+    mode: Literal["min", "max"] = Field(default="min", validate_default=True)
+    auto_insert_metric_name: bool = Field(default=False, validate_default=True)
+    every_n_train_steps: Optional[int] = Field(
+        default=None, ge=1, le=10, validate_default=True
+    )
+    train_time_interval: Optional[timedelta] = Field(
+        default=None, validate_default=True
+    )
+    every_n_epochs: Optional[int] = Field(
+        default=None, ge=1, le=10, validate_default=True
+    )
+    save_last: Optional[Literal[True, False, "link"]] = Field(
+        default=True, validate_default=True
+    )
+    save_top_k: int = Field(default=3, ge=1, le=10, validate_default=True)
+
+
+class EarlyStoppingModel(BaseModel):
+    """_summary_.
+
+    Parameters
+    ----------
+    BaseModel : _type_
+        _description_
+    """
+
+    model_config = ConfigDict(
+        validate_assignment=True,
+    )
+
+    monitor: Literal["val_loss"] = Field(default="val_loss", validate_default=True)
+    patience: int = Field(default=3, ge=1, le=10, validate_default=True)
+    mode: Literal["min", "max", "auto"] = Field(default="min", validate_default=True)
+    min_delta: float = Field(default=0.0, ge=0.0, le=1.0, validate_default=True)
+    check_finite: bool = Field(default=True, validate_default=True)
+    stop_on_nan: bool = Field(default=True, validate_default=True)
+    verbose: bool = Field(default=False, validate_default=True)
+    restore_best_weights: bool = Field(default=True, validate_default=True)
+    auto_lr_find: bool = Field(default=False, validate_default=True)
+    auto_lr_find_patience: int = Field(default=3, ge=1, le=10, validate_default=True)
+    auto_lr_find_mode: Literal["min", "max", "auto"] = Field(
+        default="min", validate_default=True
+    )
+    auto_lr_find_direction: Literal["forward", "backward"] = Field(
+        default="backward", validate_default=True
+    )
+    auto_lr_find_max_lr: float = Field(
+        default=10.0, ge=0.0, le=1e6, validate_default=True
+    )
+    auto_lr_find_min_lr: float = Field(
+        default=1e-8, ge=0.0, le=1e6, validate_default=True
+    )
+    auto_lr_find_num_training: int = Field(
+        default=100, ge=1, le=1e6, validate_default=True
+    )
+    auto_lr_find_divergence_threshold: float = Field(
+        default=5.0, ge=0.0, le=1e6, validate_default=True
+    )
+    auto_lr_find_accumulate_grad_batches: int = Field(
+        default=1, ge=1, le=1e6, validate_default=True
+    )
+    auto_lr_find_stop_divergence: bool = Field(default=True, validate_default=True)
+    auto_lr_find_step_scale: float = Field(default=0.1, ge=0.0, le=10)

careamics/config/configuration_example.py

@@ -0,0 +1,89 @@
+from .algorithm_model import AlgorithmConfig
+from .architectures import UNetModel
+from .configuration_model import Configuration
+from .data_model import DataConfig
+from .optimizer_models import LrSchedulerModel, OptimizerModel
+from .support import (
+    SupportedActivation,
+    SupportedAlgorithm,
+    SupportedArchitecture,
+    SupportedData,
+    SupportedLogger,
+    SupportedLoss,
+    SupportedOptimizer,
+    SupportedPixelManipulation,
+    SupportedScheduler,
+    SupportedTransform,
+)
+from .training_model import TrainingConfig
+
+
+def full_configuration_example() -> Configuration:
+    """Returns a dictionnary representing a full configuration example.
+
+    Returns
+    -------
+    Configuration
+        Full configuration example.
+    """
+    experiment_name = "Full example"
+    algorithm_model = AlgorithmConfig(
+        algorithm=SupportedAlgorithm.N2V.value,
+        loss=SupportedLoss.N2V.value,
+        model=UNetModel(
+            architecture=SupportedArchitecture.UNET.value,
+            in_channels=1,
+            num_classes=1,
+            depth=2,
+            num_channels_init=32,
+            final_activation=SupportedActivation.NONE.value,
+            n2v2=True,
+        ),
+        optimizer=OptimizerModel(
+            name=SupportedOptimizer.ADAM.value, parameters={"lr": 0.0001}
+        ),
+        lr_scheduler=LrSchedulerModel(
+            name=SupportedScheduler.REDUCE_LR_ON_PLATEAU.value,
+        ),
+    )
+    data_model = DataConfig(
+        data_type=SupportedData.ARRAY.value,
+        patch_size=(256, 256),
+        batch_size=8,
+        axes="YX",
+        transforms=[
+            {
+                "name": SupportedTransform.NORMALIZE.value,
+            },
+            {
+                "name": SupportedTransform.NDFLIP.value,
+                "is_3D": False,
+            },
+            {
+                "name": SupportedTransform.XY_RANDOM_ROTATE90.value,
+                "is_3D": False,
+            },
+            {
+                "name": SupportedTransform.N2V_MANIPULATE.value,
+                "roi_size": 11,
+                "masked_pixel_percentage": 0.2,
+                "strategy": SupportedPixelManipulation.MEDIAN.value,
+            },
+        ],
+        mean=0.485,
+        std=0.229,
+        dataloader_params={
+            "num_workers": 4,
+        },
+    )
+    training_model = TrainingConfig(
+        num_epochs=30,
+        logger=SupportedLogger.WANDB.value,
+    )
+
+    return Configuration(
+        experiment_name=experiment_name,
+        algorithm_config=algorithm_model,
+        data_config=data_model,
+        training_config=training_model,
+    )