Model formats

tfhub.dev hosts the following model formats: SavedModel, TF1 Hub format, TF.js and TFLite. This page provides an overview of each model format.

TensorFlow formats

tfhub.dev hosts TensorFlow models in the SavedModel format and TF1 Hub format. We recommend using models in the standardized SavedModel format instead of the deprecated TF1 Hub format when possible.

SavedModel

SavedModel is the recommended format for sharing TensorFlow models. You can learn more about the SavedModel format in the TensorFlow SavedModel guide.

You can browse SavedModels on tfhub.dev by using the TF2 version filter on the tfhub.dev browse page or by following this link.

You can use SavedModels from tfhub.dev without depending on the tensorflow_hub library, since this format is a part of core TensorFlow.

Learn more about SavedModels on TF Hub:

TF1 Hub format

The TF1 Hub format is a custom serialization format used in by TF Hub library. The TF1 Hub format is similar to the SavedModel format of TensorFlow 1 on a syntactic level (same file names and protocol messages) but semantically different to allow for module reuse, composition and re-training (e.g., different storage of resource initializers, different tagging conventions for metagraphs). The easiest way to tell them apart on disk is the presence or absence of the tfhub_module.pb file.

You can browse models in the TF1 Hub format on tfhub.dev by using the TF1 version filter on the tfhub.dev browse page or by following this link.

Learn more about models in TF1 Hub format on TF Hub:

TFLite format

The TFLite format is used for on-device inference. You can learn more at the TFLite documentation.

You can browse TF Lite models on tfhub.dev by using the TF Lite model format filter on the tfhub.dev browse page or by following this link.

TFJS format

The TF.js format is used for in-browser ML. You can learn more at the TF.js documentation.

You can browse TF.js models on tfhub.dev by using the TF.js model format filter on the tfhub.dev browse page or by following this link.