## JAX Projects

- huf: haiku utilities and framework.
- spax: Sparse operations and utilities.
- grax: Graph neural network implementations.
- deqx: Deep Equilibrium operations and haiku modules.

## Tensorfow Utilities

- tfbm: High level decorator-based interface and CLI and tensorflow benchmarks.
- kblocks: Keras blocks with dependency injection and an efficient, dynamically configurable CLI.
- meta-model: A framework for simultaneously building data map functions and learned models for model-dependent data preprocessing pipelines.
- tfrng: Unified interface for different random number generation implementations and transforms for deterministic pipelines.
- tf_marching_cubes: peicewise-differentiable marching cubes implementations.
- tf_nearest_neighbour: brute-force kernels and
`tf.py_func`

hacks for KDTree implementations. - sdf_renderer: differentiable signed distance function rendering in tensorflow.

## Dataset Repositories

Data IO and cleaning is a necessary evil of almost all machine learning research. I maintain the following repositories for downloading and preprocessing publicly available datasets using tensorflow-datasets.

- shape-tfds: 3D shape datasets.
- events-tfds: Event stream datasets
- graph-tfds: Graph datasets

## Reproduced Work

- vog_vgg: Models for semantic segmentation based on
`VGG`

network architecture and`PASCAL_VOC`

dataset. - depth_denoising: Models for denoising depth data. Currently supports end-to-end structured prediction energy networks.