basic block

basic block

basic block (no BN)

basic block (BN)

basic block (BN)

basic block (no BN)

basic block (BN)

basic block (BN)

basic block

basic block (no BN)

basic block (BN)

basic block (BN)

Discriminator for GAN loss

basic block (no BN)

basic block (BN)

basic block (no BN)

basic block (no BN)

basic block (BN)

basic block (no BN)

basic block

GAN loss

basic block

basic block

basic block (no BN)

basic block (BN)

basic block (no BN)

basic block

Vgg19 network for perceptual loss

AdaAT operator

audio encoder

audio encoder

Data Parallel with a replication callback. An replication callback `__data_parallel_replicate__` of each module will be invoked after being

image encoder

image encoder

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

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

syncnet

use syncnet to compute perception loss

A re-implementation of batch normalization, used for testing the numerical stability. Author: acgtyrant See also: https://github

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

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{Va

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{Va