Tensorflow学习--tensorboard

一、在 layer 中为 Weights, biases 设置变化图表
with tf.name_scope(‘xxxx’)
tf.summary.histogram(layer_name + ‘/xxx’,xxxx)

def add_layer(inputs , in_size, out_size,n_layer, activation_function=None):
    ## add one more layer and return the output of this layer
    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]),name='W')              
              tf.summary.histogram(layer_name + '/weights', Weights) 
         with tf.name_scope('biases'):
              biases = tf.Variable(tf.zeros([1,out_size])+0.1, name='b')           
              tf.summary.histogram(layer_name + '/biases', biases) 
         with tf.name_scope('Wx_plus_b'):
              Wx_plus_b = tf.add(tf.matmul(inputs,Weights), biases)

         if activation_function is None:
            outputs=Wx_plus_b
         else:
            outputs= activation_function(Wx_plus_b)
         tf.summary.histogram(layer_name + '/outputs', outputs) 

    return outputs

二、设置loss的变化图
使用tf.scalar_summary()

with tf.name_scope('loss'):
     loss= tf.reduce_mean(tf.reduce_sum(
              tf.square(ys- prediction), reduction_indices=[1]))

     tf.summary.scalar('loss', loss) 

三、合并所有训练图
使用tf.summary.merge_all()

sess= tf.Session()
merged = tf.summary.merge_all() # tensorflow >= 0.12
writer = tf.summary.FileWriter("logs/", sess.graph)
sess.run(tf.global_variables_initializer()) 

四、训练数据
merged 也需要run 才能发挥作用

for i in range(1000):
   sess.run(train_step, feed_dict={xs:x_data, ys:y_data})
   if i%50 == 0:
      rs = sess.run(merged,feed_dict={xs:x_data,ys:y_data})
      writer.add_summary(rs, i)

五、在 tensorboard 中查看效果
程序运行完毕之后, 会产生logs目录 , 在logs文件夹的化桑层目录，使用命令 tensorboard –logdir=logs,浏览器中输入使用 http://localhost:6006，查看效果

原文请参考：