Skip to content

Brightness Operator¤

Adjust image brightness for data augmentation.

See Also¤

datarax.operators.modality.image.brightness_operator ¤

BrightnessOperator - Operator for image brightness adjustment.

This operator extends ModalityOperator to provide brightness-only transformations.

Key Features:

  • Single-purpose: Only brightness adjustment (no contrast)
  • Simplified config with brightness_range parameter
  • Cleaner for composition in pipelines

Examples:

Basic usage:

config = BrightnessOperatorConfig(
    field_key="image",
    brightness_range=(-0.2, 0.2)
)
op = BrightnessOperator(config, rngs=rngs)

logger module-attribute ¤

logger = getLogger(__name__)

BrightnessOperatorConfig dataclass ¤

BrightnessOperatorConfig(cacheable: bool = False, batch_stats_fn: Callable | Module | None = None, precomputed_stats: dict[str, Any] | None = None, stochastic: bool = False, stream_name: str | None = None, batch_strategy: str = 'vmap', *, field_key: str, target_key: str | None = None, auxiliary_fields: list[str] | None = None, clip_range: tuple[float, float] | None = (0.0, 1.0), preserve_auxiliary: bool = True, validate_domain_constraints: bool = True, brightness_range: tuple[float, float] = (-0.2, 0.2), brightness_delta: float = 0.0)

Bases: ModalityOperatorConfig

Configuration for BrightnessOperator.

Extends ModalityOperatorConfig with brightness-specific parameters.

Attributes:

Name Type Description
clip_range tuple[float, float] | None

Range for clipping output values. Default: (0.0, 1.0) for normalized images. Overrides parent default of None.
brightness_range tuple[float, float]

Range for random brightness adjustment in stochastic mode. Format: (min_delta, max_delta). Default: (-0.2, 0.2)
brightness_delta float

Fixed brightness adjustment for deterministic mode. Only used when stochastic=False. Default: 0.0
Note

Use brightness_range=(-max_delta, max_delta) for symmetric adjustments, e.g., brightness_range=(-0.2, 0.2) for ±0.2 brightness changes.

clip_range class-attribute instance-attribute ¤

clip_range: tuple[float, float] | None = field(default=(0.0, 1.0), kw_only=True)

brightness_range class-attribute instance-attribute ¤

brightness_range: tuple[float, float] = field(default=(-0.2, 0.2), kw_only=True)

brightness_delta class-attribute instance-attribute ¤

brightness_delta: float = field(default=0.0, kw_only=True)

cacheable class-attribute instance-attribute ¤

cacheable: bool = False

batch_stats_fn class-attribute instance-attribute ¤

batch_stats_fn: Callable | Module | None = None

precomputed_stats class-attribute instance-attribute ¤

precomputed_stats: dict[str, Any] | None = None

stochastic class-attribute instance-attribute ¤

stochastic: bool = False

stream_name class-attribute instance-attribute ¤

stream_name: str | None = None

batch_strategy class-attribute instance-attribute ¤

batch_strategy: str = 'vmap'

field_key class-attribute instance-attribute ¤

field_key: str = field(kw_only=True)

target_key class-attribute instance-attribute ¤

target_key: str | None = field(default=None, kw_only=True)

auxiliary_fields class-attribute instance-attribute ¤

auxiliary_fields: list[str] | None = field(default=None, kw_only=True)

preserve_auxiliary class-attribute instance-attribute ¤

preserve_auxiliary: bool = field(default=True, kw_only=True)

validate_domain_constraints class-attribute instance-attribute ¤

validate_domain_constraints: bool = field(default=True, kw_only=True)

BrightnessOperator ¤

BrightnessOperator(config: BrightnessOperatorConfig, *, rngs: Rngs)

Bases: ModalityOperator

Image brightness transformation operator.

Applies brightness adjustment to images using additive delta

output = input + brightness_delta

Supports three modes:

  • Deterministic: Fixed brightness_delta from config
  • Stochastic: Random delta generated per batch item
  • Learnable: Trainable brightness parameters (via subclass)

The operator uses element-level apply() design:

  • apply(): Operates on single element (H,W,C) without batch dimension
  • apply_batch(): Handles batches via vmap

Examples:

Deterministic mode:

config = BrightnessOperatorConfig(
    field_key="image",
    brightness_delta=0.1,
    stochastic=False
)
operator = BrightnessOperator(config, rngs=nnx.Rngs(0))
result, _, _ = operator.apply(data, {}, {})

Stochastic mode:

config = BrightnessOperatorConfig(
    field_key="image",
    brightness_range=(-0.2, 0.2),  # Matches max_delta=0.2
    stochastic=True,
    stream_name="augment"
)
operator = BrightnessOperator(config, rngs=nnx.Rngs(0, augment=1))
random_params = operator.generate_random_params(rng, data_shapes)
result, _, _ = operator.apply(data, {}, {}, random_params=random_params)

Parameters:

Name Type Description Default
config BrightnessOperatorConfig

BrightnessOperatorConfig specifying transformation parameters

 required
rngs Rngs

Flax NNX random number generator state

 required
Note

For learnable transformations, create a subclass that: 1. Adds nnx.Param fields in its init 2. Overrides apply() to use those parameters

config instance-attribute ¤

config: BrightnessOperatorConfig = config

rngs instance-attribute ¤

rngs = rngs

name instance-attribute ¤

name = static(name)

stochastic instance-attribute ¤

stochastic = static(stochastic)

stream_name instance-attribute ¤

stream_name = static(stream_name)

apply ¤

apply(data: dict[str, Any], state: dict[str, Any], metadata: dict[str, Any], random_params: dict[str, Any] | None = None, stats: dict[str, Any] | None = None) -> tuple[dict[str, Any], dict[str, Any], dict[str, Any]]

Apply brightness transformation to data.

This method demonstrates the standard pattern for using base class helpers: 1. Extract field using _extract_field (handles KeyError gracefully) 2. Apply transformation 3. Apply clip_range using _apply_clip_range 4. Remap field using _remap_field (handles target_key logic)

Parameters:

Name Type Description Default
data dict[str, Any]

Input data dictionary containing the image field

 required
state dict[str, Any]

Operator state (unused for stateless transformations)

 required
metadata dict[str, Any]

Metadata dictionary (passed through unchanged)

 required
random_params dict[str, Any] | None

Optional random parameters for stochastic mode. Expected keys: 'brightness'

 None
stats dict[str, Any] | None

Optional statistics dictionary (unused)

 None

Returns:

Type Description
tuple[dict[str, Any], dict[str, Any], dict[str, Any]]

Tuple of (transformed_data, state, metadata)

generate_random_params ¤

generate_random_params(rng: Array, data_shapes: dict[str, tuple[int, ...]]) -> dict[str, Any]

Generate random parameters for stochastic mode.

Creates random brightness values within the configured range, one value per batch item. These arrays are later distributed by apply_batch() via vmap, so each apply() call receives a scalar value.

Parameters:

Name Type Description Default
rng Array

JAX random number generator key

 required
data_shapes dict[str, tuple[int, ...]]

Dictionary mapping field keys to their shapes. Used to determine batch size.

 required

Returns:

Type Description
dict[str, Any]

Dictionary containing:

  • 'brightness': Array of shape (batch_size,) with per-element brightness deltas

get_operation_stats ¤

get_operation_stats() -> dict[str, int]

Get operation statistics.

Note: This method converts JAX arrays to Python ints for introspection. It is intended for use outside of JIT-compiled functions.

Returns:

Type Description
dict[str, int]

Dictionary with 'applied_count' and 'skipped_count'

reset_operation_stats ¤

reset_operation_stats() -> None

Reset operation statistics to zero.

Note: Creates new JAX arrays to reset the counters.

compute_statistics ¤

compute_statistics(data: Any) -> dict[str, Any] | None

Compute statistics from data using batch_stats_fn.

If batch_stats_fn is not configured, returns None. Computed statistics are cached in _computed_stats.

Parameters:

Name Type Description Default
data Any

Input data to compute statistics from

 required

Returns:

Type Description
dict[str, Any] | None

Dictionary of statistics, or None if no batch_stats_fn configured

get_statistics ¤

get_statistics() -> dict[str, Any] | None

Get current statistics.

Returns precomputed_stats if configured (unless reset was called), otherwise returns cached computed statistics, or None if no statistics available.

Returns:

Type Description
dict[str, Any] | None

Dictionary of statistics, or None if no statistics available

set_statistics ¤

set_statistics(stats: dict[str, Any]) -> None

Manually set statistics.

This overwrites any previously computed statistics and clears reset flag.

Parameters:

Name Type Description Default
stats dict[str, Any]

Dictionary of statistics to set

 required

reset_statistics ¤

reset_statistics() -> None

Reset all statistics to None.

This clears both computed statistics and marks that precomputed_stats should be ignored (via internal flag). After reset, get_statistics() will return None until new statistics are set or computed.

reset_cache ¤

reset_cache() -> None

Clear the cache.

Only has effect if cacheable=True in config.

copy ¤

copy(*, config: DataraxModuleConfig | None = None, rngs: Rngs | None = None, name: str | None = None) -> DataraxModule

Create a copy of this module with optional config/parameter changes.

This allows creating a new module instance with modified configuration while preserving other attributes. Useful for hyperparameter tuning.

Parameters:

Name Type Description Default
config DataraxModuleConfig | None

New config (if None, uses current config)

 None
rngs Rngs | None

New RNG state (if None, uses current rngs)

 None
name str | None

New name (if None, uses current name)

 None

Returns:

Type Description
DataraxModule

New module instance with updated parameters

Examples:

Change configuration¤

new_config = DataraxModuleConfig(cacheable=True) new_module = module.copy(config=new_config)

Change name only¤

renamed = module.copy(name="new_name")

Note

Subclasses can override this method to provide more fine-grained control over copying, such as allowing individual config field updates without requiring dataclass replace().

get_state ¤

get_state() -> dict[str, Any]

Get module state for checkpointing.

This method implements the Checkpointable protocol using NNX state management. It extracts all state variables from the module and converts them to a serializable format.

Returns:

Type Description
dict[str, Any]

A dictionary containing the internal state of the component.

set_state ¤

set_state(state: dict[str, Any]) -> None

Restore module state from a checkpoint.

This method implements the Checkpointable protocol using NNX state management. It restores the module state from a serialized format. Restoration is strict: checkpoint structure must match module state.

Parameters:

Name Type Description Default
state dict[str, Any]

A dictionary containing the internal state to restore.

 required

Raises:

Type Description
TypeError

If state is not a dictionary.
ValueError

If checkpoint structure does not match module state.

clone ¤

clone() -> DataraxModule

Create a new instance with the same state as this module.

Uses NNX's clone function for proper deep cloning of all state.

Returns:

Type Description
DataraxModule

A new module instance with the same state.

requires_rng_streams ¤

requires_rng_streams() -> list[str] | None

Get the list of RNG streams required by this module.

Returns:

Type Description
list[str] | None

A list of required RNG stream names, or None if no RNG streams
list[str] | None

are required.

ensure_rng_streams ¤

ensure_rng_streams(stream_names: list[str]) -> None

Ensure that the required RNG streams are available.

Parameters:

Name Type Description Default
stream_names list[str]

A list of available RNG stream names.

 required

Raises:

Type Description
ValueError

If a required RNG stream is not available.

get_output_structure ¤

get_output_structure(sample_data: PyTree, sample_state: PyTree) -> tuple[PyTree, PyTree]

Declare output PyTree structure for vmap axis specification.

Default uses jax.eval_shape to discover structure automatically. Override for efficiency or when eval_shape doesn't work (e.g., data-dependent shapes).

Parameters:

Name Type Description Default
sample_data PyTree

Single element data (not batched)

 required
sample_state PyTree

Single element state (not batched)

 required

Returns:

Type Description
PyTree

Tuple of (output_data_structure, output_state_structure) with None leaves.
PyTree

The structure (keys/nesting) matters, leaf values are ignored.
Example override for operator that adds keys

def get_output_structure(self, sample_data, sample_state): out_data = { **jax.tree.map(lambda _: None, sample_data), "score": None, "alignment": None, } return out_data, sample_state

apply_batch ¤

apply_batch(batch: Batch, stats: dict[str, Any] | None = None) -> Batch

Process entire batch with vmap and optional RNG generation.

This method implements the batch processing logic for both stochastic and deterministic modes. It uses static branching on self.stochastic for JIT compilation efficiency.

The implementation delegates to _vmap_apply() for the shared computational core, then wraps the result in a Batch object.

Parameters:

Name Type Description Default
batch Batch

Input batch (Batch[Element] structure)

 required
stats dict[str, Any] | None

Optional statistics (if None, uses get_statistics())

 None

Returns:

Type Description
Batch

Transformed batch with same structure
Note

This method is concrete (not abstract). Subclasses typically don't override it, but can if they need custom batch processing logic.

output_spec ¤

output_spec(input_spec: PyTree) -> PyTree

Return the operator's output spec given an input spec.

Most operators (normalization, additive noise, simple element-wise transforms) do not change shape; the default returns input_spec unchanged. Shape-changing operators (Resize, Crop, Reshape) MUST override this method.

Parameters:

Name Type Description Default
input_spec PyTree

PyTree of jax.ShapeDtypeStruct describing the input element (matching the upstream DataSourceModule.element_spec() or another operator's output_spec).

 required

Returns:

Type Description
PyTree

PyTree of jax.ShapeDtypeStruct describing the operator's output.
PyTree

By default, equal to input_spec.