TensorBoard的使用

1.利用PyCharm创建TensorFlow程序(TensorFlow 1.1.0)

bogon:~ onefish$ python
>>> import tensorflow as tf
>>> print tf.__version__
1.1.0
#encoding:utf-8
import tensorflow as tf
import numpy as np

def add_layer(inputs,in_size,out_size,n_layer,activation_function=None):
    layer_name="layer%s" % n_layer
    with tf.name_scope(layer_name):
        with tf.name_scope('weights'):
            Weights = tf.Variable(tf.random_normal([in_size,out_size]))
            tf.summary.histogram(layer_name+"/weights",Weights)
        with tf.name_scope('biases'):
            biases = tf.Variable(tf.zeros([1,out_size])+0.1)
            tf.summary.histogram(layer_name+"/biases",biases) #可视化观看变量
        with tf.name_scope('Wx_plus_b'):
            Wx_plus_b = tf.matmul(inputs,Weights)+biases #inputs*Weight+biases
            tf.summary.histogram(layer_name+"/Wx_plus_b",Wx_plus_b) #可视化观看变量
        if activation_function is None:
            outputs = Wx_plus_b
        else:
            outputs = activation_function(Wx_plus_b)
        tf.summary.histogram(layer_name+"/outputs",outputs) #可视化观看变量
        return outputs

#创建数据x_data,y_data
x_data = np.linspace(-1,1,300)[:,np.newaxis] #[-1,1]区间,300个单位,np.newaxis增加维度
noise = np.random.normal(0,0.05,x_data.shape) #噪点
y_data = np.square(x_data)-0.5+noise

with tf.name_scope('inputs'): #结构化
    xs = tf.placeholder(tf.float32,[None,1],name='x_input')
    ys = tf.placeholder(tf.float32,[None,1],name='y_input')

#三层神经,输入层(1个神经元),隐藏层(10神经元),输出层(1个神经元)
l1 = add_layer(xs,1,10,n_layer=1,activation_function=tf.nn.relu) #隐藏层
prediction = add_layer(l1,10,1,n_layer=2,activation_function=None) #输出层

#predition值与y_data差别
with tf.name_scope('loss'):
    loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1])) #square()平方,sum()求和,mean()平均值
    tf.summary.scalar('loss',loss) #可视化观看常量
with tf.name_scope('train'):
    train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss) #0.1学习效率,minimize(loss)减小loss误差

init = tf.global_variables_initializer()
sess = tf.Session()
#合并到Summary中
merged = tf.summary.merge_all()
#选定可视化存储目录
writer = tf.summary.FileWriter("~/Desktop/",sess.graph)
sess.run(init) #先执行init

#训练1k次
for i in range(1000):
    sess.run(train_step,feed_dict={xs:x_data,ys:y_data})
    if i%50==0:
        result = sess.run(merged,feed_dict={xs:x_data,ys:y_data}) #merged也是需要run的
        writer.add_summary(result,i) #result是summary类型的,需要放入writer中,i步数(x轴)

2.在PyCharm中运行该程序,运行结果如下

/Users/onefish/anaconda/bin/python /Users/onefish/Python/TFtest/FirstTF.py
2017-06-14 15:31:07.786890: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-06-14 15:31:07.786910: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-06-14 15:31:07.786914: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-06-14 15:31:07.786919: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-06-14 15:31:07.786923: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.

Process finished with exit code 0

3.运行结束后,可以通过PyCharm自带的console执行TensorBoard命令去读取log文件。
这里需要注意的是log文件存放的位置,并不是在系统的~/Desktop/,运行之后在项目中生成了一个Desktop的文件夹,如图:


WX20170614-163309@2x.png

4.在PyCharm中运行

onefish:TFtest onefish$ tensorboard --logdir=/Users/onefish/Python/TFtest/Desop 
WX20170614-163740@2x.png

5.访问127.0.0.1:6006

WX20170614-163907@2x.png

推荐阅读更多精彩内容