tensorflow——tensorboard入门总结

简介

tensorboard 是tensorflow的一个可视化工具，可以简便看网络图、loss等评估指标曲线。

使用方法

1、首先要用tf.summary.scalar(name, variable)创建一个节点，用于保存这一层的权重，name是新建节点名称，val=variable是网络图中变量名。
2、利用 tf.summary.FileWriter(filepath, graph) 来保存所有节点信息，filepath是权重文件名称，graph是要保存的图
3、利用新建节点的方法：add_summary方法将在训练或测试时候把对应权重写入文件。
4、关闭文件： close()
训练完，用下面命令使得数据在浏览器可视化

 tensorboard  --logdir filepath --port  port_number
eg.
 tensorboard  --logdir tf_logs/ --port 7007

例子

代码

import tensorflow as tf
import os
os.environ['CUDA_VISIBLE_DEVICES']='0'  #set gpu mode 
config = tf.ConfigProto()                                            
config.gpu_options.per_process_gpu_memory_fraction = 0.1
import numpy as np
from sklearn.datasets import fetch_california_housing
from sklearn.preprocessing import StandardScaler
housing = fetch_california_housing()
m, n = housing.data.shape
scaler = StandardScaler()
scaled_housing_data = scaler.fit_transform(housing.data)
scaled_housing_data_plus_bias = np.c_[np.ones((m, 1)), scaled_housing_data]


from datetime import datetime

now = datetime.utcnow().strftime("%Y%m%d%H%M%S") # log path
root_logdir = "tf_logs"
logdir = "{}/run-{}/".format(root_logdir, now) # log name

n_epochs = 1000
learning_rate = 0.01

X = tf.placeholder(tf.float32, shape=(None, n + 1), name="X")
y = tf.placeholder(tf.float32, shape=(None, 1), name="y")
theta = tf.Variable(tf.random_uniform([n + 1, 1], -1.0, 1.0, seed=42), name="theta")
y_pred = tf.matmul(X, theta, name="predictions")
error = y_pred - y
mse = tf.reduce_mean(tf.square(error), name="mse")
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
training_op = optimizer.minimize(mse)

init = tf.global_variables_initializer()

mse_summary = tf.summary.scalar('MSE', mse) # init scalar
file_writer = tf.summary.FileWriter(logdir, tf.get_default_graph()) # new file

n_epochs = 10
batch_size = 100
n_batches = int(np.ceil(m / batch_size))
with tf.Session() as sess:                                                    
    sess.run(init)                                                              

    for epoch in range(n_epochs):                                           
        for batch_index in range(n_batches):
            X_batch, y_batch = fetch_batch(epoch, batch_index, batch_size)
            if batch_index % 10 == 0:
                summary_str = mse_summary.eval(feed_dict={X: X_batch, y: y_batch})
                step = epoch * n_batches + batch_index
                file_writer.add_summary(summary_str, step) # add
            sess.run(training_op, feed_dict={X: X_batch, y: y_batch})

    best_theta = theta.eval()  
file_writer.close()

结果

tensorflow——tensorboard入门总结