convolutional¶
Collection of Convolutional Models constructors.
Interfaces
Primitive Interface to be used by all |
Decoders
Primitive Model for all decoder (i.e., transpose convolution) based architecture. |
|
Fully Convolutional Decoder. |
Encoders
Primitive Model for all encoder (i.e., convolution) based architecture. |
|
Fully Convolutional Encoder. |
Autoencoders
Primitive Model for all convolutional autoencoders. |
|
Primitive Model for all fully convolutional autoencoders. |
UNet
UNet Architecture |
|
Semantic UNet |
|
Functional UNET Implementation |
Discriminators
Multi-Scale discriminator. |
|
Pix2Pix discriminator: The last layer is an image in which each pixels is the probability of being fake or real. |
Pix2PixHD
Local Enhancer module of the Pix2PixHD architecture. |
|
Global Generator from pix2pixHD paper: |
Modules
Collection of Fully Convolutional Autoencoders |
|
Discriminators |
|
Collection of Decoders (i.e., GANs’ Generators) models. |
|
Collection of Encoders (i.e., GANs’ Discriminators) models. |
|
Primitive Convolutional interfaces. |
|
UNET implementations. |
|
Pix2Pix HD Implementation See: “High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs” [1]_ |