Downloads · 30 days
16
3% of all-time downloads
keras-io/GauGAN-Image-generation
GauGAN-Image-generation is a machine learning model from keras-io. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for tf-keras.
In this, GauGAN architecture has been implemented for conditional image generation which was proposed in Semantic Image Synthesis with Spatially-Adaptive Normalization.
Downloads · 30 days
16
3% of all-time downloads
All-time downloads
558
Public
Repo size
1.3 GB
Likes
9
Public
Click a slice to open those files.
.data-00000-of-000011.3 GB · 99%
From the Hugging Face model README
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
Full credits go to Soumik Rakshit & Sayak Paul
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:
| name | learning_rate | decay | rho | momentum | epsilon | centered | training_precision |
|---|---|---|---|---|---|---|---|
| RMSprop | 0.0010000000474974513 | 0.0 | 0.8999999761581421 | 0.0 | 1e-07 | False | float32 |
