ParameterServerStrategy でパラメータサーバーをトレーニングする

pip install portpicker

2024-01-11 18:21:25.783779: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2024-01-11 18:21:25.783829: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2024-01-11 18:21:25.785347: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered

def create_in_process_cluster(num_workers, num_ps):
  """Creates and starts local servers and returns the cluster_resolver."""
  worker_ports = [portpicker.pick_unused_port() for _ in range(num_workers)]
  ps_ports = [portpicker.pick_unused_port() for _ in range(num_ps)]

  cluster_dict = {}
  cluster_dict["worker"] = ["localhost:%s" % port for port in worker_ports]
  if num_ps > 0:
    cluster_dict["ps"] = ["localhost:%s" % port for port in ps_ports]

  cluster_spec = tf.train.ClusterSpec(cluster_dict)

  # Workers need some inter_ops threads to work properly.
  worker_config = tf.compat.v1.ConfigProto()
  if multiprocessing.cpu_count() < num_workers + 1:
    worker_config.inter_op_parallelism_threads = num_workers + 1

  for i in range(num_workers):
    tf.distribute.Server(
        cluster_spec,
        job_name="worker",
        task_index=i,
        config=worker_config,
        protocol="grpc")

  for i in range(num_ps):
    tf.distribute.Server(
        cluster_spec,
        job_name="ps",
        task_index=i,
        protocol="grpc")

  cluster_resolver = tf.distribute.cluster_resolver.SimpleClusterResolver(
      cluster_spec, rpc_layer="grpc")
  return cluster_resolver

# Set the environment variable to allow reporting worker and ps failure to the
# coordinator. This is a workaround and won't be necessary in the future.
os.environ["GRPC_FAIL_FAST"] = "use_caller"

NUM_WORKERS = 3
NUM_PS = 2
cluster_resolver = create_in_process_cluster(NUM_WORKERS, NUM_PS)

variable_partitioner = (
    tf.distribute.experimental.partitioners.MinSizePartitioner(
        min_shard_bytes=(256 << 10),
        max_shards=NUM_PS))

strategy = tf.distribute.ParameterServerStrategy(
    cluster_resolver,
    variable_partitioner=variable_partitioner)

INFO:tensorflow:`tf.distribute.experimental.ParameterServerStrategy` is initialized with cluster_spec: ClusterSpec({'ps': ['localhost:44073', 'localhost:33727'], 'worker': ['localhost:33687', 'localhost:35065', 'localhost:39575']})
INFO:tensorflow:ParameterServerStrategyV2 is now connecting to cluster with cluster_spec: ClusterSpec({'ps': ['localhost:44073', 'localhost:33727'], 'worker': ['localhost:33687', 'localhost:35065', 'localhost:39575']})
INFO:tensorflow:ParameterServerStrategy (CentralStorageStrategy if you are using a single machine) with compute_devices = ['/job:chief/replica:0/task:0/device:GPU:0', '/job:chief/replica:0/task:0/device:GPU:1', '/job:chief/replica:0/task:0/device:GPU:2', '/job:chief/replica:0/task:0/device:GPU:3'], variable_device = '/device:CPU:0'
INFO:tensorflow:ParameterServerStrategy (CentralStorageStrategy if you are using a single machine) with compute_devices = ['/job:chief/replica:0/task:0/device:GPU:0', '/job:chief/replica:0/task:0/device:GPU:1', '/job:chief/replica:0/task:0/device:GPU:2', '/job:chief/replica:0/task:0/device:GPU:3'], variable_device = '/device:CPU:0'
INFO:tensorflow:Number of GPUs on workers: 4
INFO:tensorflow:Number of GPUs on workers: 4

global_batch_size = 64

x = tf.random.uniform((10, 10))
y = tf.random.uniform((10,))

dataset = tf.data.Dataset.from_tensor_slices((x, y)).shuffle(10).repeat()
dataset = dataset.batch(global_batch_size)
dataset = dataset.prefetch(2)

with strategy.scope():
  model = tf.keras.models.Sequential([tf.keras.layers.Dense(10)])

  model.compile(tf.keras.optimizers.legacy.SGD(), loss="mse", steps_per_execution=10)

working_dir = "/tmp/my_working_dir"
log_dir = os.path.join(working_dir, "log")
ckpt_filepath = os.path.join(working_dir, "ckpt")
backup_dir = os.path.join(working_dir, "backup")

callbacks = [
    tf.keras.callbacks.TensorBoard(log_dir=log_dir),
    tf.keras.callbacks.ModelCheckpoint(filepath=ckpt_filepath),
    tf.keras.callbacks.BackupAndRestore(backup_dir=backup_dir),
]

model.fit(dataset, epochs=5, steps_per_epoch=20, callbacks=callbacks)

/tmpfs/src/tf_docs_env/lib/python3.9/site-packages/tensorflow/python/data/ops/dataset_ops.py:462: UserWarning: To make it possible to preserve tf.data options across serialization boundaries, their implementation has moved to be part of the TensorFlow graph. As a consequence, the options value is in general no longer known at graph construction time. Invoking this method in graph mode retains the legacy behavior of the original implementation, but note that the returned value might not reflect the actual value of the options.
  warnings.warn("To make it possible to preserve tf.data options across "
Epoch 1/5
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Waiting for all global closures to be finished.
INFO:tensorflow:Waiting for all global closures to be finished.
INFO:tensorflow:Assets written to: /tmp/my_working_dir/ckpt/assets
INFO:tensorflow:Assets written to: /tmp/my_working_dir/ckpt/assets
20/20 - 4s - loss: 0.9102 - 4s/epoch - 203ms/step
Epoch 2/5
INFO:tensorflow:Waiting for all global closures to be finished.
INFO:tensorflow:Waiting for all global closures to be finished.
INFO:tensorflow:Assets written to: /tmp/my_working_dir/ckpt/assets
INFO:tensorflow:Assets written to: /tmp/my_working_dir/ckpt/assets
20/20 - 1s - loss: 0.7032 - 1s/epoch - 60ms/step
Epoch 3/5
INFO:tensorflow:Waiting for all global closures to be finished.
INFO:tensorflow:Waiting for all global closures to be finished.
WARNING:tensorflow:5 out of the last 5 calls to <function MultiDeviceSaver.save.<locals>.tf_function_save at 0x7f6f08236790> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.
WARNING:tensorflow:5 out of the last 5 calls to <function MultiDeviceSaver.save.<locals>.tf_function_save at 0x7f6f08236790> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.
INFO:tensorflow:Assets written to: /tmp/my_working_dir/ckpt/assets
INFO:tensorflow:Assets written to: /tmp/my_working_dir/ckpt/assets
WARNING:tensorflow:6 out of the last 6 calls to <function MultiDeviceSaver.save.<locals>.tf_function_save at 0x7f6f0845a280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.
WARNING:tensorflow:6 out of the last 6 calls to <function MultiDeviceSaver.save.<locals>.tf_function_save at 0x7f6f0845a280> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.
20/20 - 1s - loss: 0.5557 - 554ms/epoch - 28ms/step
Epoch 4/5
INFO:tensorflow:Waiting for all global closures to be finished.
INFO:tensorflow:Waiting for all global closures to be finished.
INFO:tensorflow:Assets written to: /tmp/my_working_dir/ckpt/assets
INFO:tensorflow:Assets written to: /tmp/my_working_dir/ckpt/assets
20/20 - 1s - loss: 0.4427 - 554ms/epoch - 28ms/step
Epoch 5/5
INFO:tensorflow:Waiting for all global closures to be finished.
INFO:tensorflow:Waiting for all global closures to be finished.
INFO:tensorflow:Assets written to: /tmp/my_working_dir/ckpt/assets
INFO:tensorflow:Assets written to: /tmp/my_working_dir/ckpt/assets
20/20 - 1s - loss: 0.3580 - 553ms/epoch - 28ms/step
<keras.src.callbacks.History at 0x7f6f146b7fa0>

feature_vocab = [
    "avenger", "ironman", "batman", "hulk", "spiderman", "kingkong", "wonder_woman"
]
label_vocab = ["yes", "no"]

with strategy.scope():
  feature_lookup_layer = tf.keras.layers.StringLookup(
      vocabulary=feature_vocab,
      mask_token=None)
  label_lookup_layer = tf.keras.layers.StringLookup(
      vocabulary=label_vocab,
      num_oov_indices=0,
      mask_token=None)

  raw_feature_input = tf.keras.layers.Input(
      shape=(3,),
      dtype=tf.string,
      name="feature")
  feature_id_input = feature_lookup_layer(raw_feature_input)
  feature_preprocess_stage = tf.keras.Model(
      {"features": raw_feature_input},
      feature_id_input)

  raw_label_input = tf.keras.layers.Input(
      shape=(1,),
      dtype=tf.string,
      name="label")
  label_id_input = label_lookup_layer(raw_label_input)

  label_preprocess_stage = tf.keras.Model(
      {"label": raw_label_input},
      label_id_input)

def feature_and_label_gen(num_examples=200):
  examples = {"features": [], "label": []}
  for _ in range(num_examples):
    features = random.sample(feature_vocab, 3)
    label = ["yes"] if "avenger" in features else ["no"]
    examples["features"].append(features)
    examples["label"].append(label)
  return examples

examples = feature_and_label_gen()

def dataset_fn(_):
  raw_dataset = tf.data.Dataset.from_tensor_slices(examples)

  train_dataset = raw_dataset.map(
      lambda x: (
          {"features": feature_preprocess_stage(x["features"])},
          label_preprocess_stage(x["label"])
      )).shuffle(200).batch(32).repeat()
  return train_dataset

# These variables created under the `Strategy.scope` will be placed on parameter
# servers in a round-robin fashion.
with strategy.scope():
  # Create the model. The input needs to be compatible with Keras processing layers.
  model_input = tf.keras.layers.Input(
      shape=(3,), dtype=tf.int64, name="model_input")

  emb_layer = tf.keras.layers.Embedding(
      input_dim=len(feature_lookup_layer.get_vocabulary()), output_dim=16384)
  emb_output = tf.reduce_mean(emb_layer(model_input), axis=1)
  dense_output = tf.keras.layers.Dense(
      units=1, activation="sigmoid",
      kernel_regularizer=tf.keras.regularizers.L2(1e-4),
  )(emb_output)
  model = tf.keras.Model({"features": model_input}, dense_output)

  optimizer = tf.keras.optimizers.legacy.RMSprop(learning_rate=0.1)
  accuracy = tf.keras.metrics.Accuracy()

assert len(emb_layer.weights) == 2
assert emb_layer.weights[0].shape == (4, 16384)
assert emb_layer.weights[1].shape == (4, 16384)

print(emb_layer.weights[0].device)
print(emb_layer.weights[1].device)

/job:ps/replica:0/task:1/device:CPU:0
/job:ps/replica:0/task:0/device:CPU:0

@tf.function
def step_fn(iterator):

  def replica_fn(batch_data, labels):
    with tf.GradientTape() as tape:
      pred = model(batch_data, training=True)
      per_example_loss = tf.keras.losses.BinaryCrossentropy(
          reduction=tf.keras.losses.Reduction.NONE)(labels, pred)
      loss = tf.nn.compute_average_loss(per_example_loss)
      model_losses = model.losses
      if model_losses:
        loss += tf.nn.scale_regularization_loss(tf.add_n(model_losses))
    gradients = tape.gradient(loss, model.trainable_variables)

    optimizer.apply_gradients(zip(gradients, model.trainable_variables))

    actual_pred = tf.cast(tf.greater(pred, 0.5), tf.int64)
    accuracy.update_state(labels, actual_pred)
    return loss

  batch_data, labels = next(iterator)
  losses = strategy.run(replica_fn, args=(batch_data, labels))
  return strategy.reduce(tf.distribute.ReduceOp.SUM, losses, axis=None)

coordinator = tf.distribute.coordinator.ClusterCoordinator(strategy)

@tf.function
def per_worker_dataset_fn():
  return strategy.distribute_datasets_from_function(dataset_fn)

per_worker_dataset = coordinator.create_per_worker_dataset(per_worker_dataset_fn)
per_worker_iterator = iter(per_worker_dataset)

num_epochs = 4
steps_per_epoch = 5
for i in range(num_epochs):
  accuracy.reset_states()
  for _ in range(steps_per_epoch):
    coordinator.schedule(step_fn, args=(per_worker_iterator,))
  # Wait at epoch boundaries.
  coordinator.join()
  print("Finished epoch %d, accuracy is %f." % (i, accuracy.result().numpy()))

INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Reduce to /device:CPU:0 then broadcast to ('/replica:0/device:CPU:0',).
INFO:tensorflow:Waiting for all global closures to be finished.
INFO:tensorflow:Waiting for all global closures to be finished.
Finished epoch 0, accuracy is 0.636824.
INFO:tensorflow:Waiting for all global closures to be finished.
INFO:tensorflow:Waiting for all global closures to be finished.
Finished epoch 1, accuracy is 0.427365.
INFO:tensorflow:Waiting for all global closures to be finished.
INFO:tensorflow:Waiting for all global closures to be finished.
Finished epoch 2, accuracy is 1.000000.
INFO:tensorflow:Waiting for all global closures to be finished.
INFO:tensorflow:Waiting for all global closures to be finished.
Finished epoch 3, accuracy is 1.000000.

loss = coordinator.schedule(step_fn, args=(per_worker_iterator,))
print("Final loss is %f" % loss.fetch())

Final loss is 0.184862

for _ in range(total_steps):
  coordinator.schedule(step_fn, args=(per_worker_iterator,))
while not coordinator.done():
  time.sleep(10)
  # Do something like logging metrics or writing checkpoints.

eval_dataset = tf.data.Dataset.from_tensor_slices(
    feature_and_label_gen(num_examples=16)).map(
          lambda x: (
              {"features": feature_preprocess_stage(x["features"])},
              label_preprocess_stage(x["label"])
          )).batch(8)

eval_accuracy = tf.keras.metrics.Accuracy()

for batch_data, labels in eval_dataset:
  pred = model(batch_data, training=False)
  actual_pred = tf.cast(tf.greater(pred, 0.5), tf.int64)
  eval_accuracy.update_state(labels, actual_pred)

print("Evaluation accuracy: %f" % eval_accuracy.result())

Evaluation accuracy: 1.000000

with strategy.scope():
  # Define the eval metric on parameter servers.
  eval_accuracy = tf.keras.metrics.Accuracy()

@tf.function
def eval_step(iterator):
  def replica_fn(batch_data, labels):
    pred = model(batch_data, training=False)
    actual_pred = tf.cast(tf.greater(pred, 0.5), tf.int64)
    eval_accuracy.update_state(labels, actual_pred)
  batch_data, labels = next(iterator)
  strategy.run(replica_fn, args=(batch_data, labels))

def eval_dataset_fn():
  return tf.data.Dataset.from_tensor_slices(
      feature_and_label_gen(num_examples=16)).map(
          lambda x: (
              {"features": feature_preprocess_stage(x["features"])},
              label_preprocess_stage(x["label"])
          )).shuffle(16).repeat().batch(8)

per_worker_eval_dataset = coordinator.create_per_worker_dataset(eval_dataset_fn)
per_worker_eval_iterator = iter(per_worker_eval_dataset)

eval_steps_per_epoch = 2
for _ in range(eval_steps_per_epoch):
  coordinator.schedule(eval_step, args=(per_worker_eval_iterator,))
coordinator.join()
print("Evaluation accuracy: %f" % eval_accuracy.result())

WARNING:tensorflow:4 GPUs are allocated per worker. Please use DistributedDataset by calling strategy.experimental_distribute_dataset or strategy.distribute_datasets_from_function to make best use of GPU resources
WARNING:tensorflow:4 GPUs are allocated per worker. Please use DistributedDataset by calling strategy.experimental_distribute_dataset or strategy.distribute_datasets_from_function to make best use of GPU resources
WARNING:tensorflow:4 GPUs are allocated per worker. Please use DistributedDataset by calling strategy.experimental_distribute_dataset or strategy.distribute_datasets_from_function to make best use of GPU resources
WARNING:tensorflow:4 GPUs are allocated per worker. Please use DistributedDataset by calling strategy.experimental_distribute_dataset or strategy.distribute_datasets_from_function to make best use of GPU resources
WARNING:tensorflow:4 GPUs are allocated per worker. Please use DistributedDataset by calling strategy.experimental_distribute_dataset or strategy.distribute_datasets_from_function to make best use of GPU resources
WARNING:tensorflow:4 GPUs are allocated per worker. Please use DistributedDataset by calling strategy.experimental_distribute_dataset or strategy.distribute_datasets_from_function to make best use of GPU resources
INFO:tensorflow:Waiting for all global closures to be finished.
INFO:tensorflow:Waiting for all global closures to be finished.
Evaluation accuracy: 1.000000

checkpoint_dir = ...
eval_model = ...
eval_data = ...
checkpoint = tf.train.Checkpoint(model=eval_model)

for latest_checkpoint in tf.train.checkpoints_iterator(
    checkpoint_dir):
  try:
    checkpoint.restore(latest_checkpoint).expect_partial()
  except (tf.errors.OpError,) as e:
    # checkpoint may be deleted by training when it is about to read it.
    continue

  # Optionally add callbacks to write summaries.
  eval_model.evaluate(eval_data)

  # Evaluation finishes when it has evaluated the last epoch.
  if latest_checkpoint.endswith('-{}'.format(train_epochs)):
    break

os.environ["TF_CONFIG"] = json.dumps({
    "cluster": {
        "worker": ["host1:port", "host2:port", "host3:port"],
        "ps": ["host4:port", "host5:port"],
        "chief": ["host6:port"]
    },
    "task": {"type": "worker", "index": 1}
})

os.environ["TF_CONFIG"] = json.dumps({
    "cluster": {
        "evaluator": ["host7:port"]
    },
    "task": {"type": "evaluator", "index": 0}
})

cluster_resolver = tf.distribute.cluster_resolver.TFConfigClusterResolver()
if cluster_resolver.task_type in ("worker", "ps"):
  # Start a TensorFlow server and wait.
elif cluster_resolver.task_type == "evaluator":
  # Run sidecar evaluation
else:
  # Run the coordinator.

# Set the environment variable to allow reporting worker and ps failure to the
# coordinator. This is a workaround and won't be necessary in the future.
os.environ["GRPC_FAIL_FAST"] = "use_caller"

server = tf.distribute.Server(
    cluster_resolver.cluster_spec(),
    job_name=cluster_resolver.task_type,
    task_index=cluster_resolver.task_id,
    protocol=cluster_resolver.rpc_layer or "grpc",
    start=True)
server.join()

checkpoint_manager = tf.train.CheckpointManager(
    tf.train.Checkpoint(model=model, optimizer=optimizer),
    checkpoint_dir,
    max_to_keep=3)
if checkpoint_manager.latest_checkpoint:
  checkpoint = checkpoint_manager.checkpoint
  checkpoint.restore(
      checkpoint_manager.latest_checkpoint).assert_existing_objects_matched()

global_steps = int(optimizer.iterations.numpy())
starting_epoch = global_steps // steps_per_epoch

for _ in range(starting_epoch, num_epochs):
  for _ in range(steps_per_epoch):
    coordinator.schedule(step_fn, args=(per_worker_iterator,))
  coordinator.join()
  checkpoint_manager.save()

steps_per_invocation = 10

@tf.function
def step_fn(iterator):
  for _ in range(steps_per_invocation):
    features, labels = next(iterator)
    def replica_fn(features, labels):
      ...

    strategy.run(replica_fn, args=(features, labels))