Module: tf.saved_model
Stay organized with collections
Save and categorize content based on your preferences.
Public API for tf.saved_model namespace.
Classes
class Asset: Represents a file asset to hermetically include in a SavedModel.
class SaveOptions: Options for saving to SavedModel.
Functions
contains_saved_model(...): Checks whether the provided export directory could contain a SavedModel.
load(...): Load a SavedModel from export_dir.
save(...): Exports the Trackable object obj to SavedModel format.
Other Members
ASSETS_DIRECTORY = 'assets' ASSETS_KEY = 'saved_model_assets' CLASSIFY_INPUTS = 'inputs' CLASSIFY_METHOD_NAME = 'tensorflow/serving/classify' CLASSIFY_OUTPUT_CLASSES = 'classes' CLASSIFY_OUTPUT_SCORES = 'scores' DEBUG_DIRECTORY = 'debug' DEBUG_INFO_FILENAME_PB = 'saved_model_debug_info.pb' DEFAULT_SERVING_SIGNATURE_DEF_KEY = 'serving_default' GPU = 'gpu' PREDICT_INPUTS = 'inputs' PREDICT_METHOD_NAME = 'tensorflow/serving/predict' PREDICT_OUTPUTS = 'outputs' REGRESS_INPUTS = 'inputs' REGRESS_METHOD_NAME = 'tensorflow/serving/regress' REGRESS_OUTPUTS = 'outputs' SAVED_MODEL_FILENAME_PB = 'saved_model.pb' SAVED_MODEL_FILENAME_PBTXT = 'saved_model.pbtxt' SAVED_MODEL_SCHEMA_VERSION = 1 SERVING = 'serve' TPU = 'tpu' TRAINING = 'train' VARIABLES_DIRECTORY = 'variables' VARIABLES_FILENAME = 'variables'
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2020-10-01 UTC.
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# Module: tf.saved_model\n\n\u003cbr /\u003e\n\n|------------------------------------------------------------------------|\n| [TensorFlow 1 version](/versions/r1.15/api_docs/python/tf/saved_model) |\n\nPublic API for tf.saved_model namespace.\n\nClasses\n-------\n\n[`class Asset`](../tf/saved_model/Asset): Represents a file asset to hermetically include in a SavedModel.\n\n[`class SaveOptions`](../tf/saved_model/SaveOptions): Options for saving to SavedModel.\n\nFunctions\n---------\n\n[`contains_saved_model(...)`](../tf/saved_model/contains_saved_model): Checks whether the provided export directory could contain a SavedModel.\n\n[`load(...)`](../tf/saved_model/load): Load a SavedModel from `export_dir`.\n\n[`save(...)`](../tf/saved_model/save): Exports the Trackable object `obj` to [SavedModel format](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/saved_model/README.md).\n\nOther Members\n-------------\n\n- `ASSETS_DIRECTORY = 'assets'`\n- `ASSETS_KEY = 'saved_model_assets'`\n- `CLASSIFY_INPUTS = 'inputs'`\n- `CLASSIFY_METHOD_NAME = 'tensorflow/serving/classify'`\n- `CLASSIFY_OUTPUT_CLASSES = 'classes'`\n- `CLASSIFY_OUTPUT_SCORES = 'scores'`\n- `DEBUG_DIRECTORY = 'debug'`\n- `DEBUG_INFO_FILENAME_PB = 'saved_model_debug_info.pb'`\n- `DEFAULT_SERVING_SIGNATURE_DEF_KEY = 'serving_default'`\n- `GPU = 'gpu'`\n- `PREDICT_INPUTS = 'inputs'`\n- `PREDICT_METHOD_NAME = 'tensorflow/serving/predict'`\n- `PREDICT_OUTPUTS = 'outputs'`\n- `REGRESS_INPUTS = 'inputs'`\n- `REGRESS_METHOD_NAME = 'tensorflow/serving/regress'`\n- `REGRESS_OUTPUTS = 'outputs'`\n- `SAVED_MODEL_FILENAME_PB = 'saved_model.pb'`\n- `SAVED_MODEL_FILENAME_PBTXT = 'saved_model.pbtxt'`\n- `SAVED_MODEL_SCHEMA_VERSION = 1`\n- `SERVING = 'serve'`\n- `TPU = 'tpu'`\n- `TRAINING = 'train'`\n- `VARIABLES_DIRECTORY = 'variables'`\n- `VARIABLES_FILENAME = 'variables'`"]]
TensorFlow 1 version