mnist 필기체 식별

15248 단어 21개 항목
데이터 세트download를 다운로드합니다.py
# coding:utf-8
#  tensorflow.examples.tutorials.mnist    。  TensorFlow    MNIST        
from tensorflow.examples.tutorials.mnist import input_data
#  MNIST_data/   MNIST  。           ,       
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

#          
print(mnist.train.images.shape)  # (55000, 784)
print(mnist.train.labels.shape)  # (55000, 10)

#          
print(mnist.validation.images.shape)  # (5000, 784)
print(mnist.validation.labels.shape)  # (5000, 10)

#          
print(mnist.test.images.shape)  # (10000, 784)
print(mnist.test.labels.shape)  # (10000, 10)

#     0        
print(mnist.train.images[0, :])

배열을 그림save 로 저장pic.py
#coding: utf-8
from tensorflow.examples.tutorials.mnist import input_data
import scipy.misc
import os

#   MNIST   。          。
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

#           MNIST_data/raw/    
#               
save_dir = 'MNIST_data/raw/'
if not os.path.exists(save_dir):
    os.makedirs(save_dir)




#    20   
# for i in range(20):
    #    ,mnist.train.images[i, :]    i   (   0  )
    image_array = mnist.train.images[i, :]
    # TensorFlow  MNIST     784    ,         28x28    。
    image_array = image_array.reshape(28, 28)
    #          mnist_train_0.jpg, mnist_train_1.jpg, ... ,mnist_train_19.jpg
    filename = save_dir + 'mnist_train_%d.jpg' % i
    #  image_array     
    #   scipy.misc.toimage     ,   save    。
    scipy.misc.toimage(image_array, cmin=0.0, cmax=1.0).save(filename)

print('Please check: %s ' % save_dir)



one-hot의 label label을 표시합니다.py
# coding: utf-8
from tensorflow.examples.tutorials.mnist import input_data
import numpy as np
#   mnist   。          。
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)


#   20      label
for i in range(20):
    #   one-hot  ,  (0, 1, 0, 0, 0, 0, 0, 0, 0, 0)
    one_hot_label = mnist.train.labels[i, :]
    #   np.argmax           label
    #     1  1,    0
    label = np.argmax(one_hot_label)
    print('mnist_train_%d.jpg label: %d' % (i, label))

권적 신경 네트워크의 방식을 이용하여 훈련을 진행하다
# coding: utf-8
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data



#       
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

#      
def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

#   
def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

#     
def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                          strides=[1, 2, 2, 1], padding='SAME')


if __name__ == '__main__':
    #     
    mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
    # x         、y_           
    x = tf.placeholder(tf.float32, [None, 784])
    y_ = tf.placeholder(tf.float32, [None, 10])

    #       784        28x28     
    x_image = tf.reshape(x, [-1, 28, 28, 1])

    #       
    W_conv1 = weight_variable([5, 5, 1, 32])
    b_conv1 = bias_variable([32])
    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
    h_pool1 = max_pool_2x2(h_conv1)

    #       
    W_conv2 = weight_variable([5, 5, 32, 64])
    b_conv2 = bias_variable([64])
    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
    h_pool2 = max_pool_2x2(h_conv2)

    #     ,   1024    
    W_fc1 = weight_variable([7 * 7 * 64, 1024])
    b_fc1 = bias_variable([1024])
    h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
    #   Dropout,keep_prob      ,    0.5,    1
    keep_prob = tf.placeholder(tf.float32)
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

    #  1024       10 ,  10   
    W_fc2 = weight_variable([1024, 10])
    b_fc2 = bias_variable([10])
    y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

    #       Softmax         ,     tf.nn.softmax_cross_entropy_with_logits    
    cross_entropy = tf.reduce_mean(
        tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
    #     train_step
    train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

    #         
    correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    #   Session      
    sess = tf.InteractiveSession()
    sess.run(tf.global_variables_initializer())

    #   20000 
    for i in range(20000):
        batch = mnist.train.next_batch(50)
        #  100              
        if i % 100 == 0:
            train_accuracy = accuracy.eval(feed_dict={
                x: batch[0], y_: batch[1], keep_prob: 1.0})
            print("step %d, training accuracy %g" % (i, train_accuracy))
        train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

    #                 
    print("test accuracy %g" % accuracy.eval(feed_dict={
        x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))



기계 학습의 방식으로 훈련을 진행하다
# coding:utf-8
#   tensorflow。
#   import tensorflow as tf   TensorFlow       ,     。
import tensorflow as tf
#   MNIST     
from tensorflow.examples.tutorials.mnist import input_data
#      ,  MNIST  
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

#   x,x      (placeholder),        
x = tf.placeholder(tf.float32, [None, 784])

# W Softmax     ,   784         10    
#  TensorFlow ,      tf.Variable  
W = tf.Variable(tf.zeros([784, 10]))
# b    Softmax     ,      “   ”(bias)。
b = tf.Variable(tf.zeros([10]))

# y=softmax(Wx + b),y       
y = tf.nn.softmax(tf.matmul(x, W) + b)

# y_        ,        。
y_ = tf.placeholder(tf.float32, [None, 10])

#   ,          Tensor:y y_。
# y      ,y_        ,    y_      
#         y y_    

#   y, y_       
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y)))

#     ,                   (W b)    
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

#     Session。   Session         train_step。
sess = tf.InteractiveSession()
#               ,    。
tf.global_variables_initializer().run()
print('start training...')

#   1000     
for _ in range(1000):
    #  mnist.train  100     
    # batch_xs    (100, 784)     ,batch_ys   (100, 10)     
    # batch_xs, batch_ys        x y_
    batch_xs, batch_ys = mnist.train.next_batch(100)
    #  Session   train_step,           
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

#        
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
#        ,    Tensor
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
#  Session   Tensor    Tensor  
#              
print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))  # 0.9185

좋은 웹페이지 즐겨찾기