tensorflow教程三 tensorboard可视化工具

中文教程传送门：tensorflow中文社区http://www.tensorfly.cn/tfdoc/tutorials/overview.html

我看的教程：https://www.guru99.com/tensorboard-tutorial.html

tensorboard用来可视化Graph，还可以帮助理解、调试、优化模型。

tensorboard的菜单组成：

• Scalars: Show different useful information during the model training
• Graphs: Show the model
• Histogram: Display weights with a histogram
• Distribution: Display the distribution of the weight
• Projector: Show Principal component analysis and T-SNE algorithm. The technique uses for dimensionality reduction

神经网络是一个黑盒子，tensorboard是照进黑盒子的手电。

 

 

实例代码：

代码看不懂没关系，先知道日志文件是使用model_dir这个参数指定在’train/linreg'里面就行了。

## Import the library
import tensorflow as tf
import numpy as np


X_train = (np.random.sample((10000,5)))
y_train =  (np.random.sample((10000,1)))
X_train.shape


feature_columns = [
      tf.feature_column.numeric_column('x', shape=X_train.shape[1:])]
DNN_reg = tf.estimator.DNNRegressor(feature_columns=feature_columns,
# Indicate where to store the log file    
     model_dir='train/linreg',    
     hidden_units=[500, 300],    
     optimizer=tf.train.ProximalAdagradOptimizer(      
          learning_rate=0.1,      
          l1_regularization_strength=0.001    
      )
)


# Train the estimator
train_input = tf.estimator.inputs.numpy_input_fn(    
     x={"x": X_train},    
     y=y_train, shuffle=False,num_epochs=None)
DNN_reg.train(train_input,steps=3000) 

在train/linreg的父目录下输入指令：

tensorboard --logdir train

打开浏览器，输入http://z-Laptop:6006，回车

就可以看见tensorboard界面了