Computes and stores the average and current value

Reference: Chen, Liang-Chieh, et al. *"Rethinking Atrous Convolution for Semantic Image Segmentation."*

Ohem Cross Entropy Tensor Version

Composes several segsegtransforms together. Args: segtransforms (List[Transform]): list of segtransforms to compose. Example:

Crops the given tensor. Args: size (sequence or int): Desired output size of the crop. If size is an int instead of sequence like

Randomly mask out one or more patches from an image. Args: n_holes (int): Number of patches to cut out of each image. length (int)

Randomly mask out one or more patches from an image. Args: n_holes (int): Number of patches to cut out of each image. length (int)

Given mean and std of each channel Will normalize each channel of the torch.*Tensor (C*H*W), i.e. channel = (channel - mean) / std

Randomly resize image & label with scale factor in [scale_min, scale_max]

Randomly rotate image & label with rotate factor in [rotate_min, rotate_max]

Resize the input tensor to the given size. 'size' is a 2-element tuple or list in the order of (h, w)

Resize the long size of the input image into fix size