Update README.md

README.md

@@ -6,6 +6,8 @@ datasets:
 
 GAN model trained on [CIFAR10 (Airplane)](https://www.tensorflow.org/datasets/catalog/cifar10) and [FGVC Aircraft](https://www.robots.ox.ac.uk/~vgg/data/fgvc-aircraft/) images. The model leverages [Progressive Growing](https://arxiv.org/pdf/1710.10196.pdf) with [Spectral Normalization](https://arxiv.org/pdf/1802.05957.pdf).
 
+Try out this model [here](https://huggingface.co/spaces/PrakhAI/AIPlane).
+
 | Generated Images | Real Images (for comparison) |
 | -------- | --------- |
 | ![generated_1691259071.png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/DNio2mes1414p6cgm7K62.png) | ![image.png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/4Sp33Hl9JK2cfHzBXHXfh.png) |
@@ -26,16 +28,22 @@ The Generator uses Transposed Convolutions (2x2 kernel) with strides for upsampl
 
 # Spectral Normalization
 
-# Progressive Growing
+Spectral Normalization is a technique suggested for training GANs in [this paper](https://arxiv.org/pdf/1802.05957.pdf).
 
-Progressive Growing of GAN resolutions is suggested to improve the Quality and Stability of GAN training, especially for higher resolution models (1024x1024).
+It aims to make the Critic's (Discriminator's) outputs mathematically continuous w.r.t. the space of input images, avoiding exploding gradients.
 
-For 32x32 images of Airplanes, even a short initial round of Progressive Growing clearly has an impact:
+It works very well in practice to stabilize the training of the GAN, as demonstrated by the example below (comparison at equivalent points during training):
 
-| Flat Growing (50K steps) | Progressive Growing (50K steps) |
+| Batch Normalization | Spectral Normalization |
 | ----------- | ------------ |
-| ![image.png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/QnTET-5ae_0x11CcXeWgR.png) | ![image.png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/lT_IwqkL60M1RSxEtJLaJ.png) |
+| ![image.png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/PNbqYRjw24OhMManXaMS9.png) | ![image.png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/F8q4y2vshssfdc70jH_X2.png) |
+
+# Progressive Growing
+
+Progressive Growing of GAN resolutions is suggested to improve the Quality and Stability of GAN training, especially for higher resolution models (1024x1024).
 
-Moreover, the additional parameter cost is very small (876.6 KB vs 855.1 KB for the generator).
+For 32x32 images of Airplanes, even a short initial round of Progressive Growing provides significant improvement (comparison at equivalent points during training):
 
-# Does the model simply memorize the images?
+| Flat Growing | Progressive Growing |
+| ----------- | ------------ |
+| ![image.png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/QnTET-5ae_0x11CcXeWgR.png) | ![image.png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/F8q4y2vshssfdc70jH_X2.png) |