tensorboard 添加histogram、scalar

1. 添加输入

def add_layer(inputs,in_size,out_size,n_layer,activation_function=None):
    layer_name='layer%s'%n_layer#输出结果为layern_layer,以字符串形式

2. 编辑神经层

 tf.summary.histogram(layer_name+'weights',Weights)#纵轴是weights,表示的是Weights
 tf.summary.histogram(layer_name+'biases',biases)
 tf.summmary.histogram(layer_name+'outputs', outputs)
 l1=add_layer(xs,1,10,n_layer=1,activation_function=tf.nn.relu)
 prediction=add_layer(l1,10,1,n_layer=2,activation_function=None)

3. 看loss

tf.summary.scalar('loss',loss)#标量，在events里面看

4. 合并

merged=tf.summary.merge_all()#合并所有summary

5. sess.run

result=sess.run(merged,feed_dict={
   xs:x_data,ys:y_data})#merged也要run
writer.add_summary(result,i)#在events里每隔50步记一个点

loss图：如果呈山峰状，则是学习效率值给大了，越过最优点