mindspore.dataset.vision.c_transforms.RandomHorizontalFlip

class mindspore.dataset.vision.c_transforms.RandomHorizontalFlip(prob=0.5)[source]

Randomly flip the input image horizontally with a given probability.

Note

This operation supports running on Ascend or GPU platforms by Offload.

Parameters

prob (float, optional) – Probability of the image being flipped, which must be in range of [0, 1] (default=0.5).

Raises

TypeError – If prob is not of type float.
ValueError – If prob is not in range [0, 1].
RuntimeError – If given tensor shape is not <H, W> or <H, W, C>.

Supported Platforms:: CPU Ascend GPU

Examples

>>> transforms_list = [c_vision.Decode(), c_vision.RandomHorizontalFlip(0.75)]
>>> image_folder_dataset = image_folder_dataset.map(operations=transforms_list,
...                                                 input_columns=["image"])