trw.transforms.flip

Module Contents

Functions

flip(array: trw.basic_typing.Tensor, axis: int) → trw.basic_typing.Tensor

Flip an axis of an array

transform_batch_random_flip(array: trw.basic_typing.TensorNCX, axis: int, flip_probability: Optional[float] = 0.5, flip_choices: Sequence[bool] = None) → trw.basic_typing.TensorNCX

Randomly flip an image with a given probability

transform_batch_random_flip_joint(arrays: List[trw.basic_typing.TensorNCX], axis: int, flip_probability: float = 0.5) → List[trw.basic_typing.TensorNCX]

Randomly flip a joint images with a given probability
trw.transforms.flip.flip(array: trw.basic_typing.Tensor, axis: int) → trw.basic_typing.Tensor

Flip an axis of an array

Parameters

  • array – a numpy.ndarray or torch.Tensor n-dimensional array

  • axis – the xis to flip

Returns

an array with specified axis flipped

trw.transforms.flip.transform_batch_random_flip(array: trw.basic_typing.TensorNCX, axis: int, flip_probability: Optional[float] = 0.5, flip_choices: Sequence[bool] = None) → trw.basic_typing.TensorNCX

Randomly flip an image with a given probability

Parameters

  • array – a numpy.ndarray or torch.Tensor n-dimensional array. Samples are stored on axis 0

  • axis – the axis to flip

  • flip_probability – the probability that a sample is flipped

  • flip_choices – for each sample, True or False to indicate if the sample is flipped or not

Returns

an array

trw.transforms.flip.transform_batch_random_flip_joint(arrays: List[trw.basic_typing.TensorNCX], axis: int, flip_probability: float = 0.5) → List[trw.basic_typing.TensorNCX]

Randomly flip a joint images with a given probability

Parameters

  • arrays – a list of a numpy.ndarray or torch.Tensor n-dimensional array. Samples for each array are stored on axis 0

  • axis – the axis to flip

  • flip_probability – the probability that a sample is flipped

Returns

an array