Model Conversion

MMdnnPython

A comprehensive toolset for converting, visualizing, and managing deep learning models across multiple frameworks like TensorFlow, PyTorch, and Caffe.

Proof of concept for loading Caffe models in TensorFlowPython

Convert Caffe deep learning models to TensorFlow format for deployment and inference.

BenderSwift

An abstraction layer over MetalPerformanceShaders for crafting and running fast neural networks on iOS using TensorFlow models.

pytorch2kerasPython

Convert PyTorch models to Keras (TensorFlow backend) for deployment and interoperability.

Torch7Python

Convert Torch7 neural network models to Apple CoreML format for deployment on iOS/macOS devices.

Adventures in TensorFlow LiteJupyter Notebook

A collection of Jupyter notebooks demonstrating TensorFlow Lite model quantization, conversion, and optimization techniques for deep neural networks.

TF2JAXPython

An experimental library that converts TensorFlow functions and graphs into JAX functions for reuse and fine-tuning within JAX codebases.

DeepSeek-R1-Flax-1.5B-DistillPython

Flax (JAX) and PyTorch implementations of the DeepSeek-R1-Distill-Qwen-1.5B language model with weight conversion utilities.

gluon2kerasPython

Convert deep neural network models from Apache MXNet Gluon to Keras format for interoperability between frameworks.