#7 · Primary category： Model Zoos & Hubs
hub
A library for transfer learning by reusing parts of TensorFlow models.
Project last updated：01/17/25
GitHub Stars
3.5K
Forks
1.6K
Contributors
108
License
Apache-2.0
Why we included this project
Most teams do not train image or text encoders from scratch these days, and TensorFlow Hub is the tool that makes reuse practical inside TensorFlow. You give it a published model handle and it loads the weights as a ready-to-use Keras layer, so adding a fine-tuning head on top of an existing encoder takes a few lines instead of a training run. That removes the hassle of hosting or serving checkpoints yourself. One thing to know: model hosting moved to Kaggle Models in late 2023, so new handles live there, while older tfhub.dev links still work through the loader. If you are assembling a TensorFlow pipeline out of pre-trained components, this is the natural place to start.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
models.dev
An open-source database of AI models.
Awesome-CoreML-Models
Largest list of models for Core ML (for iOS 11+)
models
Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.
PINTO_model_zoo
A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.
huggingface_hub
The official CLI and Python client for the Hugging Face Hub.