Update README.md

README.md

@@ -9,7 +9,16 @@ tags:
 
 ## Model description
 
-More information needed
+### Image classification with ConvMixer
+
+[Keras Example Link](https://keras.io/examples/vision/convmixer/)
+
+In the [Patches Are All You Need paper](https://arxiv.org/abs/2201.09792), the authors extend the idea of using patches to train an all-convolutional network and demonstrate competitive results. Their architecture namely ConvMixer uses recipes from the recent isotrophic architectures like ViT, MLP-Mixer (Tolstikhin et al.), such as using the same depth and resolution across different layers in the network, residual connections, and so on.
+
+ConvMixer is very similar to the MLP-Mixer, model with the following key differences: Instead of using fully-connected layers, it uses standard convolution layers. Instead of LayerNorm (which is typical for ViTs and MLP-Mixers), it uses BatchNorm.
+
+Full Credits to <a href = "https://twitter.com/RisingSayak" target='_blank'> Sayak Paul </a> for this work.
+
 
 ## Intended uses & limitations
 
@@ -17,7 +26,7 @@ More information needed
 
 ## Training and evaluation data
 
-More information needed
+Trained and evaluated on [CIFAR-10](https://keras.io/api/datasets/cifar10/) dataset.
 
 ## Training procedure