InceptionC block patched for FID computation

InceptionA block patched for FID computation

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

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

First InceptionE block patched for FID computation

Second InceptionE block patched for FID computation

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

Pretrained InceptionV3 network returning feature maps

Trainer creates the model and optimizers, and uses them to updates the weights of the network while reporting losses and the latest vi

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

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

Same architecture as the image discriminator

Dataset that loads images from directories Use option --label_dir, --image_dir, --instance_dir to specify the directories. The images

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 5d input that is seen as a mini-batch of 4d inputs .. math:: y = \frac{x - mean[x]}{ \sqrt{Va