1.環境準備
打開Anaconda Prompt,執行
conda create -n tensorflow python=3.6
2.激活環境
activate tensorflow
3.查看流圖
執行下述命令:
tensorboard --logdir="D:/tensorflow_learning/my_graph"
其中,logdir是存放events文件的路徑,輸出如下:
C:\ProgramData\Anaconda3\lib\site-packages\h5py\__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
TensorBoard 1.12.0 at http://DESKTOP-XXXXXXT:6006 (Press CTRL+C to quit)
打開瀏覽器,將上面的地址粘貼到瀏覽器即可查看,即
http://DESKTOP-XXXXXX:6006
附錄
- 所使用代碼(參考21個項目玩轉深度學習):
# -*- coding: utf-8 -*-
"""
Created on Sun Mar 8 21:29:32 2020
@author: QiuMingZS
"""
import tensorflow as tf
# import the dataset
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data/', one_hot=True)
# placeholder is used as Tensor, like node
x = tf.placeholder(tf.float32, [None, 784])
# parameters to be trained
W = tf.Variable(tf.zeros([784, 10])) # weight
b = tf.Variable(tf.zeros([10])) # bias
y = tf.nn.softmax(tf.matmul(x, W) + b) # output
y_ = tf.placeholder(tf.float32, [None, 10]) # the real label
# Cross Entropy, used as loss function
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y)))
# let Cross Entropy down using Gradient Descent
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
# creat a session
sess = tf.InteractiveSession()
# initialize variables before training
tf.global_variables_initializer().run()
print('Start Training ... ')
for _ in range(1000):
batch_xs, batch_ys=mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x:batch_xs, y_:batch_ys})
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
# note: accuracy is a Tensor, not a variable
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(sess.run(accuracy, feed_dict={x:mnist.test.images, y_:mnist.test.labels}))
writer = tf.summary.FileWriter('./my_graph', sess.graph)
writer.close()