TensorFlow

计算图：Graph
节点：Node —— 运算：Operation
边：Edge 数据：Tensor —— 流：Flow
标量：
向量：
矩阵：
神经网络：
会话：Session
变量：Variable
Client、Master、Worker、Device->Allocator->Tensor
SoftMax Regression
reduction_indecies???

============

from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf

#下载数据
mnist=input_data.read_data_sets("MNIST_data/",one_hot=True)
#查看数据纬度
print(mnist.train.images.shape,mnist.train.labels.shape)
print(mnist.test.images.shape,mnist.test.labels.shape)
print(mnist.validation.images.shape,mnist.validation.labels.shape)

sess=tf.InteractiveSession()

x=tf.placeholder(tf.float32,[None,784])
W=tf.Variable(tf.zeros([784,10]))
b=tf.Variable(tf.zeros([10]))

y=tf.nn.softmax(tf.matmul(x,W)+b)
y_=tf.placeholder(tf.float32,[None,10])

#交叉熵
cross_entropy=tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y),reduction_indices=[1]))

#训练
train_step=tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

#变量初始化
tf.global_variables_initializer().run()

#载入训练数据开始训练
for i in range(1000):
    batch_xs,batch_ys=mnist.train.next_batch(100)
    train_step.run({x:batch_xs,y_:batch_ys})

#准确率计算公式
correct_prediction=tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

#在测试数据集上计算准确率
print(accuracy.eval({x:mnist.test.images,y_:mnist.test.labels}))