# MLP-Mixer with CIFAR-10

**URL:** <https://discuss.ai.google.dev/t/mlp-mixer-with-cifar-10/28319>\
**Category:** Show and Tell\
**Tags:** education, learning, keras\
**Created:** [May 25, 2021, 12:46pm UTC](https://discuss.ai.google.dev/t/mlp-mixer-with-cifar-10/28319 "2021-05-25T12:46:36Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Sayak\_Paul](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/sayak_paul/32/13002_2.png) [@Sayak\_Paul](https://discuss.ai.google.dev/u/Sayak_Paul)\
**Post date:** [May 25, 2021, 12:46pm UTC](https://discuss.ai.google.dev/t/mlp-mixer-with-cifar-10/28319/1 "2021-05-25T12:46:36Z")

</div>

Here’s my implementation of [MLP-Mixer](https://arxiv.org/abs/2105.01601), the all MLP architecture for computer vision without any use of convs and self-attention:

> **[GitHub - sayakpaul/MLP-Mixer-CIFAR10: Implements MLP-Mixer...](https://github.com/sayakpaul/MLP-Mixer-CIFAR10)**
>
> Implements MLP-Mixer (https://arxiv.org/abs/2105.01601) with the CIFAR-10 dataset.

Here’s what is included:

- Distributed training with mixed-precision.
- Visualization of the token-mixing MLP weights.
- A TensorBoard callback to keep track of the learned linear projections of the image patches.

Results are quite competitive with room for improvements for interpretability.