convolutional

Collection of Convolutional Models constructors.

Interfaces

interfaces.Conv2DInterface

Primitive Interface to be used by all ashpy.models.


Decoders

decoders.BaseDecoder

Primitive Model for all decoder (i.e., transpose convolution) based architecture.

decoders.FCNNBaseDecoder

Fully Convolutional Decoder.


Encoders

encoders.BaseEncoder

Primitive Model for all encoder (i.e., convolution) based architecture.

encoders.FCNNBaseEncoder

Fully Convolutional Encoder.


Autoencoders

autoencoders.BaseAutoencoder

Primitive Model for all convolutional autoencoders.

autoencoders.FCNNBaseAutoencoder

Primitive Model for all fully convolutional autoencoders.


UNet

unet.UNet

UNet Architecture

unet.SUNet

Semantic UNet

unet.FUNet

Functional UNET Implementation


Discriminators

discriminators.MultiScaleDiscriminator

Multi-Scale discriminator.

discriminators.PatchDiscriminator

Pix2Pix discriminator: The last layer is an image in which each pixels is the probability of being fake or real.


Pix2PixHD

pix2pixhd.LocalEnhancer

Local Enhancer module of the Pix2PixHD architecture.

pix2pixhd.GlobalGenerator

Global Generator from pix2pixHD paper:


Modules

autoencoders

Collection of Fully Convolutional Autoencoders

discriminators

Discriminators

decoders

Collection of Decoders (i.e., GANs’ Generators) models.

encoders

Collection of Encoders (i.e., GANs’ Discriminators) models.

interfaces

Primitive Convolutional interfaces.

unet

UNET implementations.

pix2pixhd

Pix2Pix HD Implementation See: “High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs” [1]_