anaconda+tensorflow
重点:
1、tf.name_scope()、 tf.summary.FileWriter(‘logs/’,sses.graph)
2、参数名、op都可以定义新的名称,如下A、B、C
3、启动tensorboard:tensorboard --logdir=C:\Users\cd\Desktop\DL\logs
4、用Google浏览器打开生成的http地址:localhost:6006
代码:
import tensorflow as tf
import numpy as np
def add_layer(inputs,in_size,out_size,activation_function=None):
with tf.name_scope('layer'):
with tf.name_scope('Wieght'):
Weight = tf.Variable(tf.random_normal([in_size,out_size]),name='W')
with tf.name_scope('biases'):
biases = tf.Variable(tf.zeros([1,out_size]) + 0.1,name='biases')
with tf.name_scope('Wx_plus_b'):
Wx_plus_b = tf.add(tf.matmul(inputs,Weight),biases,name='Wx_plus_b')
if activation_function is None:
outputs = Wx_plus_b
else:
outputs = activation_function(Wx_plus_b)
return outputs
#creat net
x_data = np.linspace(-1,1,300)[:,np.newaxis]
noise = np.random.normal(0,0.05,x_data.shape)
y_data = np.square(x_data) - 0.5 + noise
with tf.name_scope('inputs'):
xs = tf.placeholder(tf.float32,[None,1],name='x_input')
ys = tf.placeholder(tf.float32,[None,1],name='y_input')
l1 = add_layer(xs,1,10,activation_function=tf.nn.relu)
prediction = add_layer(l1,10,1,activation_function=None)
with tf.name_scope('loss'):
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]),name='loss')
with tf.name_scope('train'):
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
#merged = tf.summary.merge_all() #将图形、训练过程等数据合并在一起
writer = tf.summary.FileWriter('logs/',tf.get_default_graph())
执行代码后,找到py文件目录下找logs目录:
可以看到有一个:events.out.tfevents.前缀的文件
Anaconda Prompt的终端:
cd到logs文件所在,然后执行
tensorboard --logdir=C:\Users\cd\Desktop\DL\logs
输出http地址:
注意:用localhost:6006代替,不然会报错
打开所得:
其它问题:
要重新编译代码、更新图怎么做?
1)要去logs目录下把文件删除
2)运行代码
3)重新执行启动tensorboard命令
4)刷新tensorboard界面
如果更新后,发现tensorboard的计算图比较乱,怎么办?
是因为在内存中还存在以前的数据,清理掉就好了。
1)去logs目录下把文件删除
2)jupyter–>kernel–>restart&run all
3)重新执行启动tensorboard命令
4)刷新tensorboard界面