View source on GitHub

Convenience function to build a SavedModel suitable for serving. (deprecated)

In many common cases, saving models for serving will be as simple as:

            inputs={"x": x, "y": y},
            outputs={"z": z})

Although in many cases it's not necessary to understand all of the many ways to configure a SavedModel, this method has a few practical implications:

  • It will be treated as a graph for inference / serving (i.e. uses the tag saved_model.SERVING)
  • The SavedModel will load in TensorFlow Serving and supports the Predict API. To use the Classify, Regress, or MultiInference APIs, please use either tf.Estimator or the lower level SavedModel APIs.
  • Some TensorFlow ops depend on information on disk or other information called "assets". These are generally handled automatically by adding the assets to the GraphKeys.ASSET_FILEPATHS collection. Only assets in that collection are exported; if you need more custom behavior, you'll need to use the SavedModelBuilder.

More information about SavedModel and signatures can be found here:

session The TensorFlow session from which to save the meta graph and variables.
export_dir The path to which the SavedModel will be stored.
inputs dict mapping string input names to tensors. These are added to the SignatureDef as the inputs.
outputs dict mapping string output names to tensors. These are added to the SignatureDef as the outputs.
legacy_init_op Legacy support for op or group of ops to execute after the restore op upon a load.