tf.raw_ops.DataServiceDatasetV2 | TensorFlow v2.16.1 (original) (raw)

tf.raw_ops.DataServiceDatasetV2

Stay organized with collections Save and categorize content based on your preferences.

Creates a dataset that reads data from the tf.data service.

View aliases

Compat aliases for migration

tf.compat.v1.raw_ops.DataServiceDatasetV2

tf.raw_ops.DataServiceDatasetV2(
    dataset_id,
    processing_mode,
    address,
    protocol,
    job_name,
    consumer_index,
    num_consumers,
    max_outstanding_requests,
    iteration_counter,
    output_types,
    output_shapes,
    task_refresh_interval_hint_ms=-1,
    data_transfer_protocol='',
    target_workers='AUTO',
    cross_trainer_cache_options='',
    name=None
)

Args
dataset_id	A Tensor of type int64.
processing_mode	A Tensor of type string.
address	A Tensor of type string.
protocol	A Tensor of type string.
job_name	A Tensor of type string.
consumer_index	A Tensor of type int64.
num_consumers	A Tensor of type int64.
max_outstanding_requests	A Tensor of type int64.
iteration_counter	A Tensor of type resource.
output_types	A list of tf.DTypes that has length >= 1.
output_shapes	A list of shapes (each a tf.TensorShape or list of ints) that has length >= 1.
task_refresh_interval_hint_ms	An optional int. Defaults to -1.
data_transfer_protocol	An optional string. Defaults to "".
target_workers	An optional string. Defaults to "AUTO".
cross_trainer_cache_options	An optional string. Defaults to "".
name	A name for the operation (optional).

Returns
A Tensor of type variant.

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. Some content is licensed under the numpy license.

Last updated 2024-04-26 UTC.