README.md

README.md

@@ -6,19 +6,22 @@ tags:
 - GAN
 - spatially-adaptive normalization
 - Encoder
+- Segmentation-maps
 ---
 
 ## Model description
 
-More information needed
+In this, GauGAN architecture has been implemented for conditional image generation which was proposed in [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://arxiv.org/abs/1903.07291). 
 
-## Intended uses & limitations
+GauGAN uses a `Generative Adversarial Network (GAN)` to generate realistic images that are conditioned on cue images and segmentation maps.
 
-More information needed
+This repo contains the model for the notebook [**GauGAN for conditional image generation**](https://keras.io/examples/generative/gaugan/)
+
+Full credits go to [Soumik Rakshit](https://github.com/soumik12345) & [Sayak Paul](https://twitter.com/RisingSayak)
 
 ## Training and evaluation data
 
-More information needed
+Here, the [Facades dataset](https://cmp.felk.cvut.cz/~tylecr1/facade/) 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](https://i.imgur.com/JgAv1EW.png).
 
 ## Training procedure
 
@@ -37,4 +40,8 @@ The following hyperparameters were used during training:
 
 ![Model Image](./model.png)
 
-</details>
+</details>
+
+<center>
+Model Reproduced By <u><a href="https://github.com/robotjellyzone"><b>Kavya Bisht</b></a></u>
+</center>