Function load

tensorflow/python/saved_model/loader_impl.py:245–269

Loads the model from a SavedModel as specified by tags. Args: sess: The TensorFlow session to restore the variables. tags: Set of string tags to identify the required MetaGraphDef. These should correspond to the tags used when saving the variables using the SavedModel `sav

(sess, tags, export_dir, import_scope=None, **saver_kwargs)

    "tf.compat.v1.saved_model.load. There will be a new function for importing "
    "SavedModels in Tensorflow 2.0.")
def load(sess, tags, export_dir, import_scope=None, **saver_kwargs):
  """Loads the model from a SavedModel as specified by tags.

  Args:
    sess: The TensorFlow session to restore the variables.
    tags: Set of string tags to identify the required MetaGraphDef. These should
        correspond to the tags used when saving the variables using the
        SavedModel `save()` API.
    export_dir: Directory in which the SavedModel protocol buffer and variables
        to be loaded are located.
    import_scope: Optional `string` -- if specified, prepend this string
        followed by '/' to all loaded tensor names. This scope is applied to
        tensor instances loaded into the passed session, but it is *not* written
        through to the static `MetaGraphDef` protocol buffer that is returned.
    **saver_kwargs: Optional keyword arguments passed through to Saver.

  Returns:
    The `MetaGraphDef` protocol buffer loaded in the provided session. This
    can be used to further extract signature-defs, collection-defs, etc.

  Raises:
    RuntimeError: MetaGraphDef associated with the tags cannot be found.
  """
  loader = SavedModelLoader(export_dir)
  return loader.load(sess, tags, import_scope, **saver_kwargs)


class SavedModelLoader(object):