python获取命令行参数 flags_TensorFlow命令行参数FLAGS使用

import os

os.environ[‘TF_CPP_MIN_LOG_LEVEL‘] = ‘2‘

import tensorflow as tf

#tensorboard --logdir="./"

# 命令行参数 python x.py --max_step=500

tf.app.flags.DEFINE_integer("max_step",1000,"train step number")

FLAGS = tf.app.flags.FLAGS

def linearregression():

with tf.variable_scope("original_data"):

X = tf.random_normal([100,1],mean=0.0,stddev=1.0)

y_true = tf.matmul(X,[[0.8]]) + [[0.7]]

with tf.variable_scope("linear_model"):

weights = tf.Variable(initial_value=tf.random_normal([1,1]))

bias = tf.Variable(initial_value=tf.random_normal([1,1]))

y_predict = tf.matmul(X,weights)+bias

with tf.variable_scope("loss"):

loss = tf.reduce_mean(tf.square(y_predict-y_true))

with tf.variable_scope("optimizer"):

optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(loss)

#收集观察张量

tf.summary.scalar("losses",loss)

tf.summary.histogram("weight",weights)

tf.summary.histogram("biases",bias)

#合并收集的张量

merge = tf.summary.merge_all()

init = tf.global_variables_initializer()

saver = tf.train.Saver()

with tf.Session() as sess:

sess.run(init)

# print(weights.eval(),bias.eval())

# # 模型加载

# saver.restore(sess,"./model/linearregression")

# print(weights.eval(),bias.eval())

filewriter = tf.summary.FileWriter("./tmp",graph=sess.graph)

for i in range(FLAGS.max_step):

sess.run(optimizer)

print("loss:", sess.run(loss),i)

print("weight:", sess.run(weights))

print("bias:", sess.run(bias))

summary = sess.run(merge)

filewriter.add_summary(summary,i)

#checkpoint文件，模型保存

saver.save(sess,"./model/linearregression")

if __name__ == ‘__main__‘:

linearregression()