Shortcuts

mmagic.datasets.transforms.albu_function

Module Contents

Classes

PairedAlbuTransForms

PairedAlbuTransForms augmentation.

AlbuTransForms

AlbuTransForms augmentation.

PairedAlbuNormalize

PairedAlbuNormalize augmentation.

AlbuNormalize

AlbuNormalize augmentation.

AlbuCorruptFunction

AlbuCorruptFunction augmentation.

Functions

_resolve_aug_fn(name)

class mmagic.datasets.transforms.albu_function.PairedAlbuTransForms(size: int, lq_key: str = 'img', gt_key: str = 'gt', scope: str = 'geometric', crop: str = 'random', p: float = 0.5)[source]

Bases: mmcv.transforms.BaseTransform

PairedAlbuTransForms augmentation.

Apply the same AlbuTransforms augmentation to paired images.

transform(results)[source]

processing input results according to self.pipeline.

Parameters
  • results (dict) – contains the processed data

  • pipeline. (through the transform) –

Returns

the processed data.

Return type

results

__repr__()[source]

Return repr(self).

class mmagic.datasets.transforms.albu_function.AlbuTransForms(size: int, keys: List, scope: str = 'geometric', crop: str = 'random', p: float = 0.5)[source]

Bases: mmcv.transforms.BaseTransform

AlbuTransForms augmentation.

Apply the same AlbuTransForms augmentation to the input images.

transform(results)[source]

processing input results according to self.pipeline.

Parameters
  • results (dict) – contains the processed data

  • pipeline. (through the transform) –

Returns

the processed data.

Return type

results

__repr__()[source]

Return repr(self).

class mmagic.datasets.transforms.albu_function.PairedAlbuNormalize(lq_key: str, gt_key: str, mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), max_pixel_value: float = 255.0, always_apply: bool = False, p: float = 1.0)[source]

Bases: mmcv.transforms.BaseTransform

PairedAlbuNormalize augmentation.

Apply the same AlbuNormalize augmentation to the paired images.

transform(results)[source]

processing input results according to self.normalize.

Parameters
  • results (dict) – contains the processed data

  • pipeline. (through the transform) –

Returns

the processed data.

Return type

results

__repr__()[source]

Return repr(self).

class mmagic.datasets.transforms.albu_function.AlbuNormalize(keys: List, mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), max_pixel_value: float = 255.0, always_apply: bool = False, p: float = 1.0)[source]

Bases: mmcv.transforms.BaseTransform

AlbuNormalize augmentation.

Apply the same AlbuNormalize augmentation to the input images.

transform(results)[source]

processing input results according to self.normalize.

Parameters
  • results (dict) – contains the processed data

  • pipeline. (through the transform) –

Returns

the processed data.

Return type

results

__repr__()[source]

Return repr(self).

mmagic.datasets.transforms.albu_function._resolve_aug_fn(name)[source]
class mmagic.datasets.transforms.albu_function.AlbuCorruptFunction(keys: List[str], config: List[dict], p: float = 1.0)[source]

Bases: mmcv.transforms.BaseTransform

AlbuCorruptFunction augmentation.

Apply the same AlbuCorruptFunction augmentation to the input images.

transform(results)[source]

processing input results according to self.augs.

Parameters
  • results (dict) – contains the processed data

  • pipeline. (through the transform) –

Returns

the processed data.

Return type

results

__repr__()[source]

Return repr(self).

Read the Docs v: latest
Versions
latest
stable
0.x
Downloads
pdf
epub
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.