Two days ago just installed my Tensorflow, then by tensorflow today's Chinese website (http://www.tensorfly.cn/tfdoc/get_started/introduction.html),
Getting ready to start learning about handwriting recognition tensorflow of --mnist entry letter.
The major record what small error when running my first code I, arise.
A simple example
There are some in the introduction TensorFlow use the sample code written in Python API,
Directly used to run: An error occurred
File "D:/tensorflow/python文件/tensorflow1.py", line 37 print step, sess.run(W), sess.run(b) ^ SyntaxError: invalid syntax
Later, through an online search I found that because the code used on the official website is python2.x, and I'm using python3,
1, to change the range xrange
2, modified print format
Successful operation
Import tensorflow TF AS Import numpy NP AS # use NumPy generates dummy data (phony data), a total of 100 points. x_data = np.float32 (np.random.rand (2, 100)) # stochastic input y_data = np.dot ( [0.100, 0.200], x_data) + 0.300 # configured a linear model # B = tf.Variable (tf.zeros ([. 1 ])) W is = tf.Variable (tf.random_uniform ([. 1, 2], -1.0, 1.0 )) Y = tf.matmul (W is, x_data) + B # minimize variance Loss = tf.reduce_mean (tf.square (Y - y_data)) Optimizer = tf.train.GradientDescentOptimizer (0.5 ) Train = optimizer.minimize ( loss) # Initialize variables the init = tf.initialize_all_variables () # start FIG (Graph) Sess = tf.Session () sess.run (the init) # -fit plane for STEP in Range (0, 201 ): sess.run (Train) IF 20 is ==% STEP 0: Print (STEP, sess.run (W is), sess.run (B))
Two, mnist entry
Download the data set in the time, the official website provides two ways: First, download the code and imported into the project, the second is the direct use of python source code to automatically download and install.
Here, I was directly in python source code download and install.
#导入数据集 import input_data mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) #实现回归模型 import tensorflow as tf x = tf.placeholder("float", [None, 784]) W = tf.Variable(tf.zeros([784,10])) b = tf.Variable(tf.zeros([10])) y = tf.nn.softmax(tf.matmul(x,W) + b) #训练模型 y_ = tf.placeholder("float", [None,10]) cross_entropy = -tf.reduce_sum(y_*tf.log(y)) train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy) init = tf.initialize_all_variables() sess = tf.Session() sess.run(init) for i in range(1000): batch_xs, batch_ys = mnist.train.next_batch(100) sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys}) #评估模型 correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) print (sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
Error:
ImportError: No module named 'input_data'
将import input_data 代码换成 from tensorflow.examples.tutorials.mnist import input_data
Run successfully:
The accuracy of operating results of 92%