分布式训练

相关概念

创建 Cluster 集群

cluster = tf.train.ClusterSpec({
    "worker": [
        "worker0.example.com:2222",
        "worker1.example.com:2222",
        "worker2.example.com:2222"
    ],
    "ps": [
        "ps0.example.com:2222",
        "ps1.example.com:2222"
    ]})

# Specifying distributed devices in your model
with tf.device("/job:ps/task:0"):
  weights_1 = tf.Variable(...)
  biases_1 = tf.Variable(...)

with tf.device("/job:ps/task:1"):
  weights_2 = tf.Variable(...)
  biases_2 = tf.Variable(...)

with tf.device("/job:worker/task:7"):
  input, labels = ...
  layer_1 = tf.nn.relu(tf.matmul(input, weights_1) + biases_1)
  logits = tf.nn.relu(tf.matmul(layer_1, weights_2) + biases_2)
  # ...
  train_op = ...

with tf.Session("grpc://worker7.example.com:2222") as sess:
  for _ in range(10000):
    sess.run(train_op)

注意: **cluster spec 需要在进程启动时指定,无法实现动态的扩容或缩容,这个问题社区通过引入 Kubernetes 集群管理工具来解决 **。

LocalServer

客户端与服务器一起的版本:

# Start a TensorFlow server as a single-process "cluster".
import tensorflow as tf
c = tf.constant("Hello, distributed TensorFlow!")
server = tf.train.Server.create_local_server()
sess = tf.Session(server.target)  # Create a session on the server.
print sess.run(c)
'Hello, distributed TensorFlow!'

当然,可以将其拆分成 c/s 独立的服务:

# server
import tensorflow as tf
server = tf.train.Server.create_local_server()
server.join()

# client
import tensorflow as tf
c = tf.constant("Hello, distributed TensorFlow!")
sess = tf.Session("grpc://localhost:46685")
print sess.run(c)
'Hello, distributed TensorFlow!'

完整实例

import tensorflow as tf

# Flags for defining the tf.train.ClusterSpec
tf.app.flags.DEFINE_string("ps_hosts", "",
                           "Comma-separated list of hostname:port pairs")
tf.app.flags.DEFINE_string("worker_hosts", "",
                           "Comma-separated list of hostname:port pairs")

# Flags for defining the tf.train.Server
tf.app.flags.DEFINE_string("job_name", "","One of 'ps', 'worker'")
tf.app.flags.DEFINE_integer("task_index", 0, "Index of task within the job")

FLAGS = tf.app.flags.FLAGS

def main(_):
  ps_hosts = FLAGS.ps_hosts.split(",")
  worker_hosts = FLAGS.worker_hosts.split(",")

  # Create a cluster from the parameter server and worker hosts.
  cluster = tf.train.ClusterSpec({"ps": ps_hosts, "worker": worker_hosts})

  # Create and start a server for the local task.
  server = tf.train.Server(cluster,
                           job_name=FLAGS.job_name,
                           task_index=FLAGS.task_index)

  if FLAGS.job_name == "ps":
    server.join()
  elif FLAGS.job_name == "worker":

    # Assigns ops to the local worker by default.
    with tf.device(tf.train.replica_device_setter(
        worker_device="/job:worker/task:%d" % FLAGS.task_index,
        cluster=cluster)):

      # Build model...
      loss = ...
      global_step = tf.Variable(0)

      train_op = tf.train.AdagradOptimizer(0.01).minimize(
          loss, global_step=global_step)

      saver = tf.train.Saver()
      summary_op = tf.summary.merge_all()
      init_op = tf.global_variables_initializer()

    # Create a "supervisor", which oversees the training process.
    sv = tf.train.Supervisor(is_chief=(FLAGS.task_index == 0),
                             logdir="/tmp/train_logs",
                             init_op=init_op,
                             summary_op=summary_op,
                             saver=saver,
                             global_step=global_step,
                             save_model_secs=600)

    # The supervisor takes care of session initialization, restoring from
    # a checkpoint, and closing when done or an error occurs.
    with sv.managed_session(server.target) as sess:
      # Loop until the supervisor shuts down or 1000000 steps have completed.
      step = 0
      while not sv.should_stop() and step < 1000000:
        # Run a training step asynchronously.
        # See `tf.train.SyncReplicasOptimizer` for additional details on how to
        # perform *synchronous* training.
        _, step = sess.run([train_op, global_step])

    # Ask for all the services to stop.
    sv.stop()

if __name__ == "__main__":
  tf.app.run()
# On ps0.example.com:
$ python trainer.py \
     --ps_hosts=ps0.example.com:2222,ps1.example.com:2222 \
     --worker_hosts=worker0.example.com:2222,worker1.example.com:2222 \
     --job_name=ps --task_index=0
# On ps1.example.com:
$ python trainer.py \
     --ps_hosts=ps0.example.com:2222,ps1.example.com:2222 \
     --worker_hosts=worker0.example.com:2222,worker1.example.com:2222 \
     --job_name=ps --task_index=1
# On worker0.example.com:
$ python trainer.py \
     --ps_hosts=ps0.example.com:2222,ps1.example.com:2222 \
     --worker_hosts=worker0.example.com:2222,worker1.example.com:2222 \
     --job_name=worker --task_index=0
# On worker1.example.com:
$ python trainer.py \
     --ps_hosts=ps0.example.com:2222,ps1.example.com:2222 \
     --worker_hosts=worker0.example.com:2222,worker1.example.com:2222 \
     --job_name=worker --task_index=1
Pengfei Ni ©2021