add new dementions at the front and the tail

Compute the Dice coefficient between two binary segmentation. Dice coefficient is defined as here: https://en.wikipedia.org/wiki/S%C3%B8rense

Initialize the GANLoss class. Parameters: gan_mode (str) - - the type of GAN objective. It currently supports vanilla, lsgan, an

sum over the first and last dimention

Return a normalization layer Parameters: norm_type (str) -- the name of the normalization layer: batch | instance | none For BatchNo

Initialize a network: 1. register CPU/GPU device (with multi-GPU support); 2. initialize the network weights Parameters: net (network)

Normalizate ent to 0 - 1 :param ent: :return:

Constructs a ResNet-101 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Args: master_callback: a callback to be invoked after having collected messages from slave devices.

Compute the mean and standard-deviation with sum and square-sum. This method also maintains the moving average on the master device.

This definition generalize to real valued pred and target vector. This should be differentiable. pred: tensor with first dimension as batch

Create label tensors with the same size as the input. Parameters: prediction (tensor) - - tpyically the prediction from a discrim

Initialize network weights. Parameters: net (network) -- network to be initialized init_type (str) -- the name of an initializa

Register an slave device. Args: identifier: an identifier, usually is the device id. Returns: a `SlavePipe` objec

Main entry for the master device in each forward pass. The messages were first collected from each devices (including the master devi

in tensor fomate :param input: :param target: :return:

Calculate loss given Discriminator's output and grount truth labels. Parameters: prediction (tensor) - - tpyically the prediction