#77th of 7 in ML frameworks and libraries
models
Reference TensorFlow 2 model implementations, plus the Orbit training-loop library
- Stars
- 77.6k
- License
- custom license
- Last commit
- Oct 2026
- Last release
- Feb 2026
- Language
- Python
Checked on GitHub.
Overview
Repository of TensorFlow model implementations split into official (maintained by the TensorFlow team), research (maintained by researchers, TF1 or TF2) and a curated community list. It also includes Orbit, a lightweight library for custom TF2 training loops that works with tf.distribute on CPU, GPU and TPU. Installable as tf-models-official or the nightly tf-models-nightly package.
Who it is for: TensorFlow users needing reference model code or custom training loops
Strengths
- Official directory is maintained by the TensorFlow team against current TF2 APIs
- Orbit supports custom training loops with tf.distribute on CPU, GPU and TPU
- Published on PyPI as tf-models-official, with a daily nightly build
- Training logs on TensorBoard.dev provided for some models
Weaknesses
- Research directory is researcher-maintained and mixes TensorFlow 1 and 2 code
- tf-models-official may lag master; nightly package needed for latest changes
- Source install needs manual PYTHONPATH setup and extra requirements
- GitHub reports license as NOASSERTION, although the README states Apache 2.0
What it needs
- GPU optional
- Needs TensorFlow 2, tensorflow-text-nightly (NLP packages)
- Models: TensorFlow, TensorFlow 1 (research)
Also in ML frameworks and libraries
See all 7| Rank | Project | Score |
|---|---|---|
| 1 | transformersModel-definition library for text, vision, audio and multimodal models | 92 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd for deep learning | 89 out of 100 |
| 3 | tensorflowTensor and neural network framework with Python and C++ APIs | 80 out of 100 |
| #4 | ultralyticsPython library and CLI for training and running YOLO vision models | 77 out of 100 |
| #5 | kerasMulti-backend deep learning library running on JAX, TensorFlow and PyTorch | 70 out of 100 |