TensorFlow-mnist实际操练（矩阵运算）

版权声明：本文为博主原创文章，欢迎转载。 https://blog.csdn.net/samylee/article/details/84969002

TensorFlow-mnist实际操练（矩阵运算，非卷积运算）

硬件：NVIDIA-GTX1080

软件：Windows7、python3.6.5、tensorflow-gpu-1.4.0

一、基础知识

1、matmul's different from tf.nn.conv2d

2、None*784  x 784*10 = None*10

二、数据下载

下载链接

三、代码展示

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

def add_layer(inputs, in_size, out_size, activate_function = None):
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    Biases = tf.Variable(tf.zeros([1,out_size]) + 0.1)

    #matmul's different from tf.nn.conv2d
    Wx_plus_b = tf.matmul(inputs, Weights) + Biases #None*784  x 784*10 = None*10
    
    if activate_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activate_function(Wx_plus_b)

    return outputs

def compute_accuracy(v_xs, v_ys):
    global prediction
    y_pre = sess.run(prediction, feed_dict = {xs: v_xs})
    correct_prediction = tf.equal(tf.argmax(y_pre, 1), tf.argmax(v_ys, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))#ture to 1.0, false to 0.0
    result = sess.run(accuracy)
    return result

mnist = input_data.read_data_sets('MNIST_data/', one_hot = True)

xs = tf.placeholder(tf.float32, [None, 784])
ys = tf.placeholder(tf.float32, [None, 10])

prediction = add_layer(xs, 784, 10, activate_function = tf.nn.softmax)

cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction), reduction_indices = [1]))
optimizer = tf.train.GradientDescentOptimizer(0.5)
train_step = optimizer.minimize(cross_entropy)

init = tf.global_variables_initializer()

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 = {xs: batch_xs, ys: batch_ys})
    if i%50 == 0:
        print(compute_accuracy(mnist.test.images, mnist.test.labels))

sess.close()

四、结果展示

Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz
0.1004
0.6287
0.7282
0.7737
0.7929
0.8175
0.8315
0.8372
0.8456
0.8529
0.8572
0.8594
0.8607
0.8677
0.8613
0.8678
0.8731
0.8748
0.8752
0.8777

任何问题请加唯一QQ2258205918（名称samylee）！