记录:
Tensorboard学习笔记记录:
步骤一:
参考代码:(基于tensorflow2.5.0,tensorboard2.6.0)
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
def add_layer(inputs, in_size, out_size, activation_function=None):
with tf.name_scope('layer'):
with tf.name_scope('Weights'):
Weights = tf.Variable(tf.random_normal([in_size, out_size]), name='W')
with tf.name_scope('Bias'):
biases = tf.Variable(tf.zeros([1, out_size])+0.1, name='b')
with tf.name_scope('Wx_plus_b'):
Wx_plus_b = tf.add(tf.matmul(inputs, Weights), biases)
if activation_function is None: # activation函数自己默认是有名字的,如ReLU
outputs = Wx_plus_b
else:
outputs = activation_function(Wx_plus_b)
return outputs
# define placeholder for inputs to network
with tf.name_scope('inputs'): # 名字的象征
xs = tf.placeholder(tf.float32, [None, 1], name='x_input')
ys = tf.placeholder(tf.float32, [None, 1], name='y_input')
# add hidden layer
l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)
# add output layer
prediction = add_layer(l1, 10, 1, activation_function=None)
# the error between predictionn and real data
with tf.name_scope('loss'):
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),
reduction_indices=[1])) # 均方差
with tf.name_scope('train'):
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
sess = tf.Session()
# 定义好session之后定义writer
writer = tf.summary.FileWriter("logs/",sess.graph) # 定义框架
# important step
sess.run(tf.initialize_all_variables())
步骤二: