TwoNormDataPreprocessor¶

class mmpretrain.models.utils.data_preprocessor.TwoNormDataPreprocessor(mean=None, std=None, second_mean=None, second_std=None, pad_size_divisor=1, pad_value=0, to_rgb=False, non_blocking=False)[源代码]¶

Image pre-processor for CAE, BEiT v1/v2, etc.

Compared with the mmselfsup.SelfSupDataPreprocessor, this module will normalize the prediction image and target image with different normalization parameters.

参数:

mean (Sequence[float or int], optional) – The pixel mean of image channels. If to_rgb=True it means the mean value of R, G, B channels. If the length of mean is 1, it means all channels have the same mean value, or the input is a gray image. If it is not specified, images will not be normalized. Defaults to None.
std (Sequence[float or int], optional) – The pixel standard deviation of image channels. If to_rgb=True it means the standard deviation of R, G, B channels. If the length of std is 1, it means all channels have the same standard deviation, or the input is a gray image. If it is not specified, images will not be normalized. Defaults to None.
second_mean (Sequence[float or int], optional) – The description is like mean, it can be customized for targe image. Defaults to None.
second_std (Sequence[float or int], optional) – The description is like std, it can be customized for targe image. Defaults to None.
pad_size_divisor (int) – The size of padded image should be divisible by pad_size_divisor. Defaults to 1.
pad_value (float or int) – The padded pixel value. Defaults to 0.
to_rgb (bool) – whether to convert image from BGR to RGB. Defaults to False.
non_blocking (bool) – Whether block current process when transferring data to device. Defaults to False.

forward(data, training=False)[源代码]¶

Performs normalization and bgr2rgb conversion based on BaseDataPreprocessor. The batch_inputs in forward function is a list.

参数:

data (dict) – data sampled from dataloader.
training (bool) – Whether to enable training time augmentation. If subclasses override this method, they can perform different preprocessing strategies for training and testing based on the value of training.

返回:

Data in the same format as the: model input.

返回类型:

Tuple[torch.Tensor, Optional[list]]