https://github.com/tensorflow/hub
A library for transfer learning by reusing parts of TensorFlow models.
https://github.com/tensorflow/hub
embeddings image-classification machine-learning ml python tensorflow transfer-learning
Last synced: 6 months ago
JSON representation
A library for transfer learning by reusing parts of TensorFlow models.
- Host: GitHub
- URL: https://github.com/tensorflow/hub
- Owner: tensorflow
- License: apache-2.0
- Created: 2018-03-12T07:55:42.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2025-01-17T12:09:41.000Z (10 months ago)
- Last Synced: 2025-05-11T02:53:29.666Z (6 months ago)
- Topics: embeddings, image-classification, machine-learning, ml, python, tensorflow, transfer-learning
- Language: Python
- Homepage: https://tensorflow.org/hub
- Size: 13 MB
- Stars: 3,496
- Watchers: 152
- Forks: 1,657
- Open Issues: 15
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- Authors: AUTHORS
Awesome Lists containing this project
- awesome-starts - tensorflow/hub - A library for transfer learning by reusing parts of TensorFlow models. (Python)
- awesome-open-data-centric-ai - Tensorflow Hub
- awesome-list - TensorFlow Hub - A library for transfer learning by reusing parts of TensorFlow models (Deep Learning Framework / High-Level DL APIs)
- Awesome-Earth-Artificial-Intelligence - TensorFlow Hub - trained SavedModels that can be reused to solve new tasks with less training time and less training data. (Tools)
- awesome-python-machine-learning-resources - GitHub - 2% open · ⏱️ 23.08.2022): (Tensorflow实用程序)
- StarryDivineSky - tensorflow/hub
- my-awesome - tensorflow/hub - classification,machine-learning,ml,python,tensorflow,transfer-learning pushed_at:2025-01 star:3.5k fork:1.7k A library for transfer learning by reusing parts of TensorFlow models. (Python)
README
**TensorFlow Hub has moved to [Kaggle Models](https://kaggle.com/models)**
Starting November 15th 2023, links to [tfhub.dev](https://tfhub.dev) redirect to
their counterparts on Kaggle Models. `tensorflow_hub` will continue to support
downloading models that were initially uploaded to tfhub.dev via e.g.
`hub.load("https://tfhub.dev///")`. Although no
migration or code rewrites are explicitly required, we recommend replacing
tfhub.dev links with their Kaggle Models counterparts to improve code health and
debuggability. See FAQs [here](https://kaggle.com/tfhub-dev-faqs).
As of March 18, 2024, unmigrated model assets (see list below) were deleted and
retrieval is no longer possible. These unmigrated model assets include:
- [inaturalist/vision/embedder/inaturalist_V2](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/inaturalist/models/vision/embedder/inaturalist_V2)
- [nvidia/unet/industrial/class_1](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/nvidia/models/unet/industrial/class_1)
- [nvidia/unet/industrial/class_2](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/nvidia/models/unet/industrial/class_2)
- [nvidia/unet/industrial/class_3](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/nvidia/models/unet/industrial/class_3)
- [nvidia/unet/industrial/class_4](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/nvidia/models/unet/industrial/class_4)
- [nvidia/unet/industrial/class_5](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/nvidia/models/unet/industrial/class_5)
- [nvidia/unet/industrial/class_6](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/nvidia/models/unet/industrial/class_6)
- [nvidia/unet/industrial/class_7](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/nvidia/models/unet/industrial/class_7)
- [nvidia/unet/industrial/class_8](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/nvidia/models/unet/industrial/class_8)
- [nvidia/unet/industrial/class_9](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/nvidia/models/unet/industrial/class_9)
- [nvidia/unet/industrial/class_10](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/nvidia/models/unet/industrial/class_10)
- [silero/silero-stt/de](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/silero/models/silero-stt/de)
- [silero/silero-stt/en](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/silero/models/silero-stt/en)
- [silero/silero-stt/es](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/silero/models/silero-stt/es)
- [svampeatlas/vision/classifier/fungi_mobile_V1](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/svampeatlas/models/vision/classifier/fungi_mobile_V1)
- [svampeatlas/vision/embedder/fungi_V2](https://github.com/tensorflow/tfhub.dev/tree/master/assets/docs/svampeatlas/models/vision/embedder/fungi_V2)
# tensorflow_hub
This GitHub repository hosts the `tensorflow_hub` Python library to download
and reuse SavedModels in your TensorFlow program with a minimum amount of code,
as well as other associated code and documentation.
## Getting Started
* [Introduction](https://www.tensorflow.org/hub/)
* The asset types of [tfhub.dev](https://tfhub.dev/)
* [SavedModels for TensorFlow 2](https://github.com/tensorflow/docs/blob/master/site/en/hub/tf2_saved_model.md)
and the [Reusable SavedModel interface](https://github.com/tensorflow/docs/blob/master/site/en/hub/reusable_saved_models.md).
* Deprecated: [Models in TF1 Hub format](https://github.com/tensorflow/docs/blob/master/site/en/hub/tf1_hub_module.md)
and their [Common Signatures](https://github.com/tensorflow/docs/blob/master/site/en/hub/common_signatures/index.md)
collection.
* Using the library
* [Installation](https://github.com/tensorflow/docs/blob/master/site/en/hub/installation.md)
* [Caching model downloads](https://github.com/tensorflow/docs/blob/master/site/en/hub/caching.md)
* [Migration to TF2](https://github.com/tensorflow/docs/blob/master/site/en/hub/migration_tf2.md)
* [Model compatibility for TF1/TF2](https://github.com/tensorflow/docs/blob/master/site/en/hub/model_compatibility.md)
* [Common issues](https://github.com/tensorflow/docs/blob/master/site/en/hub/common_issues.md)
* [Build from source](https://github.com/tensorflow/docs/blob/master/site/en/hub/build_from_source.md)
* [Hosting a module](https://github.com/tensorflow/docs/blob/master/site/en/hub/hosting.md)
* Tutorials
* [TF2 Image Retraining](https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/hub/tutorials/tf2_image_retraining.ipynb)
* [TF2 Text Classification](https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/hub/tutorials/tf2_text_classification.ipynb)
* [Additional TF1 and TF2 examples](examples/README.md)
## Contributing
If you'd like to contribute to TensorFlow Hub, be sure to review the
[contribution guidelines](CONTRIBUTING.md). To contribute code to the
library itself (not examples), you will probably need to
[build from source](https://github.com/tensorflow/docs/blob/master/site/en/hub/build_from_source.md).
This project adheres to TensorFlow's
[code of conduct](https://github.com/tensorflow/tensorflow/blob/master/CODE_OF_CONDUCT.md).
By participating, you are expected to uphold this code.
We use [GitHub issues](https://github.com/tensorflow/hub/issues) for tracking
requests and bugs.
## License
[Apache License 2.0](LICENSE)