Defines the Unet submodule with skip connection. X -------------------identity---------------------- |-- downsampling -- |submodule| -

Modified Alighed Xception

A thread-safe future implementation. Used only as one-to-one pipe.

Defines a PatchGAN discriminator

Pipe for master-slave communication.

An abstract `SyncMaster` object. - During the replication, as the data parallel will trigger an callback of each module, all slave devices should

Create a Unet-based generator

Fundus segmentation dataset including 5 domain dataset one for test others for training

Define different GAN objectives. The GANLoss class abstracts away the need to create the target label tensor that has the same size as the in

Normalize a tensor image with mean and standard deviation. Args: mean (tuple): means for each channel. std (tuple): standard devia

Normalize a tensor image with mean and standard deviation. Args: mean (tuple): means for each channel. std (tuple): standard devia

Normalize a tensor image with mean and standard deviation. Args: mean (tuple): means for each channel. std (tuple): standard devia

r"""Applies Synchronized Batch Normalization over a 2d or 3d input that is seen as a mini-batch. .. math:: y = \frac{x - mean[x]}{ \sq

r"""Applies Batch Normalization over a 4d input that is seen as a mini-batch of 3d inputs .. math:: y = \frac{x - mean[x]}{ \sqrt{Var[

r"""Applies Batch Normalization over a 5d input that is seen as a mini-batch of 4d inputs .. math:: y = \frac{x - mean[x]}{ \sqrt{Var[

Convert ndarrays in sample to Tensors.

Elastic deformation of images as described in [Simard2003]_. .. [Simard2003] Simard, Steinkraus and Platt, "Best Practices for Conv