#coding=utf-8
import numpy as np
import tensorflow as tf
#python example.py --ps_hosts=127.0.0.1:2222 --worker_hosts=127.0.0.1:2224,127.0.0.1:2225 --job_name=ps --task_index=0
#python example.py --ps_hosts=127.0.0.1:2222 --worker_hosts=127.0.0.1:2224,127.0.0.1:2225 --job_name=worker --task_index=0
#python example.py --ps_hosts=127.0.0.1:2222 --worker_hosts=127.0.0.1:2224,127.0.0.1:2225 --job_name=worker --task_index=1
# Define parameters
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_float('learning_rate', 0.00003, 'Initial learning rate.')
tf.app.flags.DEFINE_integer('steps_to_validate', 1000,
'Steps to validate and print loss')
# For distributed
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")
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")
# Hyperparameters
learning_rate = FLAGS.learning_rate
steps_to_validate = FLAGS.steps_to_validate
def main(_):
ps_hosts = FLAGS.ps_hosts.split(",")
worker_hosts = FLAGS.worker_hosts.split(",")
cluster = tf.train.ClusterSpec({"ps": ps_hosts, "worker": worker_hosts})
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":
with tf.device(tf.train.replica_device_setter(
worker_device="/job:worker/task:%d" % FLAGS.task_index,
cluster=cluster)):
global_step = tf.Variable(0, name='global_step', trainable=False)
input = tf.placeholder("float")
label = tf.placeholder("float")
weight = tf.get_variable("weight", [1], tf.float32, initializer=tf.random_normal_initializer())
biase = tf.get_variable("biase", [1], tf.float32, initializer=tf.random_normal_initializer())
pred = tf.mul(input, weight) + biase
loss_value = loss(label, pred)
train_op = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss_value, global_step=global_step)
init_op = tf.initialize_all_variables()
saver = tf.train.Saver()
tf.scalar_summary('cost', loss_value)
summary_op = tf.merge_all_summaries()
sv = tf.train.Supervisor(is_chief=(FLAGS.task_index == 0),
logdir="./checkpoint/",
init_op=init_op,
summary_op=None,
saver=saver,
global_step=global_step,
save_model_secs=60)
with sv.managed_session(server.target) as sess:
step = 0
while step < 1000000:
train_x = np.random.randn(1)
train_y = 2 * train_x + np.random.randn(1) * 0.33 + 10
_, loss_v, step = sess.run([train_op, loss_value,global_step], feed_dict={input:train_x, label:train_y})
if step % steps_to_validate == 0:
w,b = sess.run([weight,biase])
print("step: %d, weight: %f, biase: %f, loss: %f" %(step, w, b, loss_v))
sv.stop()
def loss(label, pred):
return tf.square(label - pred)
if __name__ == "__main__":
tf.app.run()
tensorflow 分布式 数据并行 异步训练 between-graph 实例
最新推荐文章于 2023-05-19 08:26:45 发布
本文详细介绍了如何在TensorFlow中实现分布式的between-graph异步训练,通过这种方式,可以在多个GPU或机器上并行地训练模型,提高训练效率。内容涵盖了设置环境、定义模型、配置分布式策略以及启动训练过程的关键步骤。
摘要由CSDN通过智能技术生成