tf.compat.v1.estimator.tpu.experimental

Class to keep track of the specification for TPU embeddings.

tf.compat.v1.estimator.tpu.experimental.EmbeddingConfigSpec(
    feature_columns=None, optimization_parameters=None, clipping_limit=None,
    pipeline_execution_with_tensor_core=False,
    experimental_gradient_multiplier_fn=None, feature_to_config_dict=None,
    table_to_config_dict=None, partition_strategy='div',
    profile_data_directory=None
)

Pass this class to tf.estimator.tpu.TPUEstimator via the embedding_config_spec parameter. At minimum you need to specify feature_columns and optimization_parameters. The feature columns passed should be created with some combination of tf.tpu.experimental.embedding_column and tf.tpu.experimental.shared_embedding_columns.

TPU embeddings do not support arbitrary Tensorflow optimizers and the main optimizer you use for your model will be ignored for the embedding table variables. Instead TPU embeddigns support a fixed set of predefined optimizers that you can select from and set the parameters of. These include adagrad, adam and stochastic gradient descent. Each supported optimizer has a Parameters class in the tf.tpu.experimental namespace.

column_a = tf.feature_column.categorical_column_with_identity(...)
column_b = tf.feature_column.categorical_column_with_identity(...)
column_c = tf.feature_column.categorical_column_with_identity(...)
tpu_shared_columns = tf.tpu.experimental.shared_embedding_columns(
    [column_a, column_b], 10)
tpu_non_shared_column = tf.tpu.experimental.embedding_column(
    column_c, 10)
tpu_columns = [tpu_non_shared_column] + tpu_shared_columns
...
def model_fn(features):
  dense_features = tf.keras.layers.DenseFeature(tpu_columns)
  embedded_feature = dense_features(features)
  ...

estimator = tf.estimator.tpu.TPUEstimator(
    model_fn=model_fn,
    ...
    embedding_config_spec=tf.estimator.tpu.experimental.EmbeddingConfigSpec(
        column=tpu_columns,
        optimization_parameters=(
            tf.estimator.tpu.experimental.AdagradParameters(0.1))))

Args
`feature_columns`	All embedding `FeatureColumn`s used by model.
`optimization_parameters`	An instance of `AdagradParameters`, `AdamParameters` or `StochasticGradientDescentParameters`. This optimizer will be applied to all embedding variables specified by `feature_columns`.
`clipping_limit`	(Optional) Clipping limit (absolute value).
`pipeline_execution_with_tensor_core`	setting this to `True` makes training faster, but trained model will be different if step N and step N+1 involve the same set of embedding IDs. Please see `tpu_embedding_configuration.proto` for details.
`experimental_gradient_multiplier_fn`	(Optional) A Fn taking global step as input returning the current multiplier for all embedding gradients.
`feature_to_config_dict`	A dictionary mapping feature names to instances of the class `FeatureConfig`. Either features_columns or the pair of `feature_to_config_dict` and `table_to_config_dict` must be specified.
`table_to_config_dict`	A dictionary mapping feature names to instances of the class `TableConfig`. Either features_columns or the pair of `feature_to_config_dict` and `table_to_config_dict` must be specified.
`partition_strategy`	A string, determining how tensors are sharded to the tpu hosts. See `tf.nn.safe_embedding_lookup_sparse` for more details. Allowed value are `"div"` and `"mod"'. If`"mod"`is used, evaluation and exporting the model to CPU will not work as expected. </td> </tr><tr> <td>`profile_data_directory`	Directory where embedding lookup statistics are stored. These statistics summarize information about the inputs to the embedding lookup operation, in particular, the average number of embedding IDs per example and how well the embedding IDs are load balanced across the system. The lookup statistics are used during TPU initialization for embedding table partitioning. Collection of lookup statistics is done at runtime by profiling the embedding inputs: only 3% of input samples are profiled to minimize host CPU overhead. Once a suitable number of samples are profiled, the lookup statistics are saved to table-specific files in the profile data directory generally at the end of a TPU training loop. The filename corresponding to each table is obtained by hashing table specific parameters (e.g., table name and number of features) and global configuration parameters (e.g., sharding strategy and task count). The same profile data directory can be shared among several models to reuse embedding lookup statistics.

Raises
`ValueError`	If the feature_columns are not specified.
`TypeError`	If the feature columns are not of ths correct type (one of _SUPPORTED_FEATURE_COLUMNS, _TPU_EMBEDDING_COLUMN_CLASSES OR _EMBEDDING_COLUMN_CLASSES).
`ValueError`	If `optimization_parameters` is not one of the required types.

Attributes
`feature_columns`
`tensor_core_feature_columns`
`optimization_parameters`
`clipping_limit`
`pipeline_execution_with_tensor_core`
`experimental_gradient_multiplier_fn`
`feature_to_config_dict`
`table_to_config_dict`
`partition_strategy`
`profile_data_directory`

TensorFlow

tf.compat / v1 / v1.estimator.tpu.experimental.Overview

Args

Raises

Attributes

TensorFlow

tf

tf.audio

tf.autograph

tf.bitwise

tf.compat

tf.config

tf.data

tf.debugging

tf.distribute

tf.dtypes

tf.errors

tf.estimator

tf.experimental

tf.feature_column

tf.graph_util

tf.image

tf.initializers

tf.io

tf.keras

tf.linalg

tf.lite

tf.lookup

tf.losses

tf.math

tf.metrics

tf.nest

tf.nn

tf.optimizers

tf.quantization

tf.queue

tf.ragged

tf.random

tf.raw_ops

tf.saved_model

tf.sets

tf.signal

tf.sparse

tf.strings

tf.summary

tf.sysconfig

tf.test

tf.tpu

tf.train

tf.version

tf.xla

tf.compat / v1 / v1.estimator.tpu.experimental.Overview

Args

Raises

Attributes