深度学习解决手写数字的图片识别
深度学习解决手写数字的图片识别
用户6021899
发布于 2019-11-07 12:30:16
发布于 2019-11-07 12:30:16
本篇使用TensorFlow框架，利用MNIST手写数字数据集来演示深度学习的入门概念。其训练集共有60000个样本（图片和标签），测试集有10000个样本。手写数字的图片都是尺寸为28*28的二值图：
我们先导入必要的库：
import tensorflow as tf
import tensorflow.examples.tutorials.mnist.input_data as input_data
import os设置全连接神经网络的参数：神经网络的结构为784*500*10 （输入层784节点，1层500个节点的隐藏层，除输出层外每层的激活函数都使用ReLU, 输出层10个节点, 最后使用tf.argmax()函数求出输出层节点中最大的数的索引，范围0~9，该索引值即为手写数字的估计值）
注：上述图片仅做示意，每层节点数，以及隐藏层的层数以代码为准
#模型路径
MODEL_SAVE_PATH ="/model_path/"
MODEL_NAME = "MNIST_model1.ckpt"
INPUT_NODE = 28*28 #图片28*28像素，展平为784=28*28个输入节点
OUTPUT_NODE = 10 #输出特征为10个，对应0~9的量
BATCH_SIZE =100 # 训练批次的size
LEARNING_RATE_BASE = 0.8 #基础学习率
LEARNING_RATE_DECAY = 0.99 #学习率缩减系数
REGULARIZATION_RATE = 0.0001 # 正则率
TRAINING_STEPS = 30000 #总的训练步数
MOVING_AVERAGE_DECAY = 0.99 #移动平均缩减系数
#神经网络的结构，784*500*10 （输入层784节点，1层500个节点的隐藏层，输出层10个节点）
layer_dimension = [INPUT_NODE,500,OUTPUT_NODE]
#也可以是多个隐藏层，如 layer_dimension = [INPUT_NODE,50,100，20，UTPUT_NODE]
n_layers = len(layer_dimension) #神经网络总的层数前向传播：
def inference(input_x, avg_class, reuse = True):
'''Forward propagation'''
current_layer = input_x
in_dimension = INPUT_NODE
with tf.variable_scope("layers", reuse =reuse):
for i in range(1, n_layers):#循环
out_dimension = layer_dimension[i] # weight, bias can't be local variables, or will not be updated!!!!!!!!!
weight = tf.get_variable("weight_"+str(i), [in_dimension, out_dimension], initializer = tf.truncated_normal_initializer(stddev = 0.1))
tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)(weight))# L2 regularization
bias = tf.get_variable("bias_"+str(i), [out_dimension], initializer = tf.constant_initializer(0.0))
if avg_class == None:
if i == n_layers - 1:
current_layer = tf.matmul(current_layer, weight) + bias
else:
current_layer = tf.nn.relu(tf.matmul(current_layer, weight) +bias)
else:
if i == n_layers - 1:
current_layer = tf.matmul(current_layer, avg_class.average(weight)) + avg_class.average(bias)
else:
current_layer = tf.nn.relu(tf.matmul(current_layer, avg_class.average(weight)) + avg_class.average(bias))
in_dimension = out_dimension
return current_layer # output神经网络训练，即反向传播，以梯度下降算法优化各个权重W张量和各个偏置B张量。
def train(mnist):
'''training'''
x = tf.placeholder(tf.float32, [None, INPUT_NODE], name='x-input')
y_ = tf.placeholder(tf.float32,[None, OUTPUT_NODE], name = 'y-input')
y = inference(x, None, reuse = False)
global_step = tf.Variable(0, trainable = False)
#滑动平均模型
variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables()) # moving average applied
average_y = inference(x, variable_averages, reuse = True)
# loss
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits = y, labels = tf.argmax(y_, 1))
cross_entropy_mean = tf.reduce_mean(cross_entropy)
tf.add_to_collection('losses', cross_entropy_mean)
loss = tf.add_n(tf.get_collection('losses'))
#loss = cross_entropy_mean
#learning rate with decay
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, global_step,mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY, staircase = True)
#learning_rate = 0.01
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step = global_step)
train_op = tf.group(train_step, variables_averages_op)
correct_prediction = tf.equal(tf.argmax(average_y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))#tf.cast做类型转换
with tf.Session() as sess:
tf.global_variables_initializer().run()
validate_feed = {x: mnist.validation.images, y_ : mnist.validation.labels}
test_feed = {x: mnist.test.images, y_ : mnist.test.labels}
steps = [] # only for plot
accs = [] # only for plot
losses = [] # only for plot
for i in range(TRAINING_STEPS):
xs, ys = mnist.train.next_batch(BATCH_SIZE)
_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict = {x : xs, y_: ys})
if i % 200 == 0:
validate_acc = sess.run(accuracy, feed_dict = validate_feed)
steps.append(step); accs.append(validate_acc*100); losses.append(loss_value) # only for plot
#print("After %d training steps, validation accuracy using average model on training batch is %g%%, loss on training batch is %g"%(step, validate_acc*100,loss_value))
#saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step =global_step)
test_acc = sess.run(accuracy, feed_dict = test_feed)
print("After %d training steps, test accuracy using average model is %g%%"%
(TRAINING_STEPS, test_acc*100))
#仅用于tensorboard
writer = tf.summary.FileWriter("E://TensorBoard//test",sess.graph)
#保存神经网络模型
saver = tf.train.Saver()
saver.save(sess, r"E:\Python36\my tensorflow\ckpt files\mode_mnist.ckpt")
#only for plot#不是必要步骤
from matplotlib import pyplot as plt
import matplotlib.ticker as mtick
plt.subplot(211)
plt.plot(steps, losses,color="red")
plt.scatter(steps, losses,s=20,color="red")
plt.xlabel("step"); plt.ylabel("loss(including L2 regularization loss) on training set")
plt.subplot(212)
plt.plot(steps, accs,color="green")
plt.scatter(steps, accs,s=20,color="green")
yticks = mtick.FormatStrFormatter("%.3f%%")
plt.gca().yaxis.set_major_formatter(yticks)
plt.xlabel("step"); plt.ylabel("accuracy on training set")
plt.show()真正加载MNIST数据集，并训练模型：
def main(argv = None):
mnist = input_data.read_data_sets(r"E:\Python36\my tensorflow\MNIST_data",one_hot =True)
train(mnist)
if __name__ == "__main__":
tf.app.run()可以看出5000步以后，模型已大致收敛：
30000步迭代之后，在测试集上的准确率已高达98.5%。
After 30000 training steps, test accuracy using average model is 98.5%
下面我们利用已训练好的模型做预测：
import tensorflow as tf
import tensorflow.examples.tutorials.mnist.input_data as input_data
import matplotlib.pyplot as plt
INPUT_NODE = 28*28
OUTPUT_NODE = 10
layer_dimension = [INPUT_NODE,500,OUTPUT_NODE]
n_layers = len(layer_dimension)
def inference(input_x, avg_class, reuse = True):
current_layer = input_x
in_dimension = INPUT_NODE
with tf.variable_scope("layers", reuse =reuse):
for i in range(1, n_layers):
out_dimension = layer_dimension[i] # weight, bias can't be local variables, or will not be updated!!!!!!!!!
w = tf.get_variable("weight_"+str(i), [in_dimension, out_dimension])
b = tf.get_variable("bias_"+str(i), [out_dimension])
if avg_class == None:
if i == n_layers - 1:
current_layer = tf.matmul(current_layer, w) + b
else:
current_layer = tf.nn.relu(tf.matmul(current_layer, w) +b)
in_dimension = out_dimension
return current_layer # output
with tf.variable_scope("layers", reuse =tf.AUTO_REUSE): ####!!!!!!!!
weight1 = tf.get_variable("weight_1", [INPUT_NODE, 500])
bias1= tf.get_variable("bias_1", [500])
weight2 = tf.get_variable("weight_2", [500, OUTPUT_NODE])
bias2= tf.get_variable("bias_2", [OUTPUT_NODE])
#saver = tf.train.import_meta_graph(r"E:\Python36\my tensorflow\ckpt files\mode_mnist.ckpt.meta")
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, r"E:\Python36\my tensorflow\ckpt files\mode_mnist.ckpt")
#graph = tf.get_default_graph()
#for v in tf.global_variables():
#print(v.name)
#print(v.eval())
image_rawdata = tf.gfile.FastGFile(r"E:\Python36\MNIST picture\test\54.jpg","rb").read()
img_data = tf.image.decode_jpeg(image_rawdata)
if img_data.dtype != tf.float32:
img_data = tf.image.convert_image_dtype(img_data, dtype = tf.float32)
image_data_shaped2 = tf.reshape(img_data,(1,INPUT_NODE))# tftensor
input_x = image_data_shaped2
y = inference(input_x, avg_class=None, reuse = True)
print("y: ", sess.run(y))
print( "predict number: ", sess.run(tf.argmax(y, 1)))#output label
image_data = img_data.eval() # return a numpy array
image_data_shaped1 = image_data.reshape(image_data.shape[0],image_data.shape[1])#numpy array
#print(image_data_shaped1)
plt.imshow(image_data_shaped1,cmap='gray')
plt.show()注意，要保持神经网络的结构和训练时的一致。我们加载已训练好的模型，用它来预测测试集中的第54张图：
输出结果是：
predict number: [6]正确！
如果想要预测我们自己拍的照片，记得须先将照片转化为28*28的二值图, 用openCV实现起来很简单，不再赘述。
本文参与 腾讯云自媒体分享计划，分享自微信公众号。
原始发表：2019-11-05，如有侵权请联系 cloudcommunity@tencent.com 删除
本文分享自 Python可视化编程机器学习OpenCV 微信公众号，前往查看
如有侵权，请联系 cloudcommunity@tencent.com 删除。
本文参与 腾讯云自媒体分享计划 ，欢迎热爱写作的你一起参与！
评论
登录后参与评论
推荐阅读