In this, GauGAN architecture has been implemented for conditional image generation which was proposed in Semantic Image Synthesis with Spatially-Adaptive Normalization.
GauGAN uses a
Generative Adversarial Network (GAN) to generate realistic images that are conditioned on cue images and segmentation maps.
This repo contains the model for the notebook GauGAN for conditional image generation
Here, the Facades dataset is used for training GauGAN model. Some custom layers that were added into the model are - SPADE (SPatially-Adaptive (DE) normalization), Residual block including SPADE & Gaussian sampler. Also, the GauGAN encoder consists of a few downsampling blocks. It outputs the mean and variance of a distribution as shown in this image.
The following hyperparameters were used during training:
- Downloads last month
Unable to determine this model’s pipeline type. Check the docs .