分布式训练

strategy = tf.distribute.experimental.ParameterServerStrategy(...)
with strategy.scope():
  model = tfdf.keras.DistributedGradientBoostedTreesModel()
  distributed_train_dataset = strategy.distribute_datasets_from_function(dataset_fn)
model.fit(distributed_train_dataset)

/path/to/dataset/train-00000-of-00100
/path/to/dataset/train-00001-of-00005
/path/to/dataset/train-00002-of-00005
...

import tensorflow_decision_forests as tfdf
import tensorflow as tf

strategy = tf.distribute.experimental.ParameterServerStrategy(...)

with strategy.scope():
  model = tfdf.keras.DistributedGradientBoostedTreesModel()

model.fit_on_dataset_path(
    train_path="/path/to/dataset/train@1000",
    label_key="label_key",
    dataset_format="tfrecord+tfe")

print("Trained model")
model.summary()

import tensorflow_decision_forests as tfdf
import tensorflow as tf


def dataset_fn(context, paths):
  """Create a worker-sharded finite dataset from paths.

  Like for non-distributed training, each example should be visited exactly
  once (and by only one worker) during the training. In addition, for optimal
  training speed, the reading of the examples should be distributed among the
  workers (instead of being read by a single worker, or read and discarded
  multiple times).

  In other words, don't add a "repeat" statement and make sure to shard the
  dataset at the file level and not at the example level.
  """

  # List the dataset files
  ds_path = tf.data.Dataset.from_tensor_slices(paths)

  # Make sure the dataset is used with distributed training.
  assert context is not None


  # Split the among the workers.
  #
  # Note: The "shard" is applied on the file path. The shard should not be
  # applied on the examples directly.
  # Note: You cannot use 'context.num_input_pipelines' with ParameterServerV2.
  current_worker = tfdf.keras.get_worker_idx_and_num_workers(context)
  ds_path = ds_path.shard(
      num_shards=current_worker.num_workers,
      index=current_worker.worker_idx)

  def read_csv_file(path):
    """Reads a single csv file."""

    numerical = tf.constant([0.0], dtype=tf.float32)
    categorical_string = tf.constant(["NA"], dtype=tf.string)
    csv_columns = [
        numerical,  # feature 1
        categorical_string,  # feature 2
        numerical,  # feature 3
        # ... define the features here.
    ]
    return tf.data.experimental.CsvDataset(path, csv_columns, header=True)

  ds_columns = ds_path.interleave(read_csv_file)

  # We assume a binary classification label with the following possible values.
  label_values = ["<=50K", ">50K"]

  # Convert the text labels into integers:
  # "<=50K" => 0
  # ">50K" => 1
  init_label_table = tf.lookup.KeyValueTensorInitializer(
      keys=tf.constant(label_values),
      values=tf.constant(range(label_values), dtype=tf.int64))
  label_table = tf.lookup.StaticVocabularyTable(
      init_label_table, num_oov_buckets=1)

  def extract_label(*columns):
    return columns[0:-1], label_table.lookup(columns[-1])

  ds_dataset = ds_columns.map(extract_label)

  # The batch size has no impact on the quality of the model. However, a larger
  # batch size generally is faster.
  ds_dataset = ds_dataset.batch(500)
  return ds_dataset


strategy = tf.distribute.experimental.ParameterServerStrategy(...)
with strategy.scope():
  model = tfdf.keras.DistributedGradientBoostedTreesModel()

  train_dataset = strategy.distribute_datasets_from_function(
      lambda context: dataset_fn(context, [...list of csv files...])
  )

model.fit(train_dataset)

print("Trained model")
model.summary()

with strategy.scope():
  tuner = tfdf.tuner.RandomSearch(num_trials=30, use_predefined_hps=True)
  model = tfdf.keras.GradientBoostedTreesModel(tuner=tuner)

training_history = model.fit_on_dataset_path(
  train_path=train_path,
  label_key=label,
  dataset_format="csv",
  valid_path=test_path)

logging.info("Trained model:")
model.summary()