Generative Models
High-resolution Deep Convolutional Generative Adversarial Networks
Introduced by Curtó et al. in High-Resolution Deep Convolutional Generative Adversarial NetworksHDCGAN, or High-resolution Deep Convolutional Generative Adversarial Networks, is a DCGAN based architecture that achieves high-resolution image generation through the proper use of SELU activations. Glasses, a mechanism to arbitrarily improve the final GAN generated results by enlarging the input size by a telescope ζ is also set forth.
A video showing the training procedure on CelebA-hq can be found here.
Source: High-Resolution Deep Convolutional Generative Adversarial Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Batch Normalization
|
Normalization | |
Convolution
|
Convolutions | |
SELU
|
Activation Functions | |
Sigmoid Activation
|
Activation Functions | |
Tanh Activation
|
Activation Functions |
