断点续训
ckpt = tf.train.get_checkpoint_state(MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
# 恢复会话
saver.restore(sess, ckpt.model_checkpoint_path)
实现了给所有的w和b赋保存在ckpt中的值,实现断点续训。
def application():
testNum = input("input the num of test pictures:") # 输入要识别几张图片
for i in range(testNum):
testPic = raw_input("the path of test picture") # 给出识别图片的路径和名称
testPicArr = pre_pic(testPic) # 预处理
preValue = restore_model(testPicArr) # 喂给复现的神经网络模型
print("The prediction number is: ", preValue)
input函数可以从控制台读入数字
raw_input从控制台读入字符串
app.py
import tensorflow as tf
import numpy as np
from PIL import Image
import forward
import backward
def pre_pic(picName):
img = Image.open(picName)
reIm = img.resize((28, 28), Image.ANTIALIAS)
im_arr = np.array(reIm.convert('L')) # 变成灰度图
"""
模型要求的是黑底白字
输入的图片是白底黑字
因此要给输入图片反色
纯白色255
"""
threshold = 50
for i in range(28):
for j in range(28):
im_arr[i][j] = 255 - im_arr[i][j]
if (im_arr[i][j] < threshold):
im_arr[i][j] = 0
else:
im_arr[i][j] = 255
nm_arr = im_arr.reshape([1, 784])
nm_arr = nm_arr.astype(np.float32)
img_ready = np.multiply(nm_arr, 1.0/255.0)
return img_ready
def restore_model(testPicArr):
with tf.Graph().as_default() as tg:
# 仅需要给输入x占位
x = tf.placeholder(tf.float32, [None, forward.INPUT_MODE])
# 计算求得输出y
y = forward.forward(x, None)
# 返回预测结果索引
preValue = tf.argmax(y, 1)
# 实例化带有滑动平均值的saver
variable_averages = tf.train.ExponentialMovingAverage(backward.MOVING_AVERAGE_DECAY)
variable_to_restore = variable_averages.variables_to_restore() ####
saver = tf.train.Saver(variable_to_restore)
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(backward.MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
preValue = sess.run(preValue, feed_dict={x:testPicArr})
return preValue
else:
print("No checkpoint file found")
return -1
def application():
testNum = int(input("input the number of test pictures:"))
for i in range(testNum):
testPic = input("the path of test picture")
testPicArr = pre_pic(testPic)
preValue = restore_model(testPicArr)
print("The prediction number is: ", preValue)
def main():
application()
if __name__ == '__main__':
main()
制作数据集
tfrecords文件
tfrecords是一种二进制文件,可先将图片和标签制作成该格式的文件。使用tfrecords进行数据读取,会提高内存利用率。
用tf.train.Example的协议存储训练数据。训练数据的特征用键值对的形式表示。
如:
‘img_raw’:值 ‘label’:值
值是Byteslist/FloatList/Int64List
用SerializeToString()把数据序列化成字符串存储。
生成tfrecords文件
# 新建一个writer
writer = tf.python_io.TFRecordWriter(tfRecordName)
for 循环遍历每张图和标签:
# 把每章图片和标签装到exampl中
example = tf.train.Example(features=tf.train.Features(feature={'img_raw':tf.train.Feature(bytes_list=tf.train.BytesList(value=[img_raw)),'label':tf.train.Feature(int64_list=tf.train.Int64List(value=lables))}))
# 把example进行序列化
writer.write(example.SerializeToString)
write.close()
解析tfrecords文件
filename_queue = tf.train.string_input_producer([tfRecord_path])
reader = tf.TFRecordReader() # 新建一个reader
_, serialized_example = reader.read(filename_queue)
features = tf.parse_single_example(serialized_example,features={'img_raw':tf.FixedLenFeature([],tf.string), 'label': tf.FixdLenFeature([10],tf.int64)})
img = tf.decode_raw(feature['img_raw'],tf.uint8)
img.set_reshape([784])
img = tf.cast(img, tf.float32)*(1./255)
label = tf.cast(features['label'], tf.float32)
在backw和test的python文件中修改图片标签获取的接口
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# 图片和标签的批获取
coord.request_stop()
coord.join(threads)
import tensorflow as tf
import numpy as np
from PIL import Image
import os
image_train_path = 'mnist_data_jpg/mnist_train_jpg_60000/'
label_train_path = 'mnist_data_jpg/mnist_train_jpg_60000.txt'
tfRecord_train = 'data/mnist_train.tfrecords'
image_test_path = 'mnist_data_jpg/mnist_test_jpg_10000/'
label_test_path = 'mnist_data_jpg/mnist_test_jpg_10000.txt'
tfRecord_test = 'data/mnist_test.tfrecords'
data_path = 'data'
resize_height = 28
resize_width =28
def writer_tfRecord(tfRceordName, image_path, label_path):
writer = tf.python_io.TFRecordWriter(tfRceordName)
# 为了显示进度创建一个计数器
num_pic = 0
f = open(label_path, 'r')
contents = f.readlines()
f.close()
for content in contents:
value = content.split()
img_path = image_path + value[0]
img = Image.open(img_path)
img_raw = img.tobytes() ####
labels = [0] * 10
labels[int(value[1])] = 1
example = tf.train.Example(features=tf.train.Features(feature={
'img_raw': tf.train.Feature(bytes_list=tf.train.BytesList(value=[img_raw])),
'label': tf.train.Feature(int64_list=tf.train.Int64List(value=labels))
}))
writer.write(example.SerializeToString())
num_pic += 1
print("the number of picture: ", num_pic)
writer.close()
print("write tfrecord successfully")
# 接收待读取的tfrecord文件
def read_tfRecord(tfRecord_path):
# 新建文件名队列,告知文件名队列包括哪些文件
filename_queue = tf.train.string_input_producer([tfRecord_path])
# 新建一个reader,把读出的每一个样本保存到serialized_example中进行解序列化
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
# 标签和图片的键名应该和制作tfrecord文件的键名相同
# 标签要给出是几分类
features = tf.parse_single_example(serialized_example,
features={
'label': tf.FixedLenFeature([10], tf.int64),
'img_raw': tf.FixedLenFeature([], tf.string)
})
img = tf.decode_raw(features['img_raw'], tf.uint8)
img.set_shape([784])
img = tf.cast(img, tf.float32) * (1. / 255)
label = tf.cast(features['label'], tf.float32)
return img, label
# 批读取,批获取训练集和测试集中的图片和标签
def get_tfRecord(num, isTrain=True):
if isTrain:
tfRecord_path = tfRecord_train
else:
tfRecord_path = tfRecord_test
img, label = read_tfRecord(tfRecord_path)
# 从总样本中顺序取出capacity组数据,打乱顺序,每次输出batch_size组
img_batch, label_batch = tf.train.shuffle_batch([img, label],
batch_size=num,
num_threads=2,
capacity=1000,
min_after_dequeue=700)
return img_batch, label_batch
def generate_tfRecord():
# 判断保存路径是否存在,不存在则新建,否则返回已存在
isExists = os.path.exists(data_path)
if not isExists:
os.makedirs(data_path)
print("The directory is created successfully")
else:
print("directory is exists")
# 训练集和测试集中的图片和标签生成tfRecord文件
writer_tfRecord(tfRecord_train, image_train_path, label_train_path)
writer_tfRecord(tfRecord_test, image_test_path, label_test_path)
def main():
generate_tfRecord()
if __name__ == '__main__':
main()
forward.py
import tensorflow as tf
# 定义神经网络结构的相关参数
INPUT_MODE = 784
OUTPUT_MODE = 10
LAYER_MODE = 500
def forward(x, regularizer):
w1 = get_weight([INPUT_MODE, LAYER_MODE], regularizer)
b1 = get_bias([LAYER_MODE])
y1 = tf.nn.relu(tf.matmul(x, w1) + b1)
w2 = get_weight([LAYER_MODE, OUTPUT_MODE], regularizer)
b2 = get_bias([OUTPUT_MODE])
y = tf.matmul(y1, w2) + b2
return y
def get_weight(shape, regularizer):
w = tf.Variable(tf.truncated_normal(shape, stddev=0.1))
if regularizer != None:
tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(regularizer)(w))
return w
def get_bias(shape):
b = tf.Variable(tf.zeros(shape))
return b
backward.py
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import forward
import os
import generateds
# 每轮喂入神经网络图片数量
BATCH_SIZE = 200
# 最开始的学习率
LEARNING_RATE_BASE = 0.1
# 学习率衰减率
LEARNING_RATE_DECAY = 0.99
# 正则化系数
REGULARIZER = 0.0001
# 共训练多少轮
STEPS = 50000
# 滑动平均衰减率
MOVING_AVERAGE_DECAY = 0.99
# 模型的保存路径
MODEL_SAVE_PATH = './model/'
# 模型保存的文件名
MODEL_NAME = 'mnist_model'
train_num_examples = 60000
def backward(mnist):
x = tf.placeholder(tf.float32, [None, forward.INPUT_MODE])
y_ = tf.placeholder(tf.float32, [None, forward.OUTPUT_MODE])
y = forward.forward(x, REGULARIZER)
global_step = tf.Variable(0, trainable=False)
## 使用了滑动平均 要加入的代码
ce = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
cem = tf.reduce_mean(ce)
# 调用包含正则化的损失函数loss
loss = cem + tf.add_n(tf.get_collection('losses'))
## 指数衰减学习率
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE,
global_step,
# mnist.train.num_examples / BATCH_SIZE,
train_num_examples / BATCH_SIZE,
LEARNING_RATE_DECAY,
staircase=True)
# 定义训练过程
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
## 定义滑动平均
ema = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
ema_op = ema.apply(tf.trainable_variables())
with tf.control_dependencies([train_step, ema_op]):
train_op = tf.no_op(name='train')
saver = tf.train.Saver()
img_batch, label_batch = generateds.get_tfRecord(BATCH_SIZE, isTrain=True) ####
with tf.Session() as sess:
init_op = tf.global_variables_initializer()
sess.run(init_op)
ckpt = tf.train.get_checkpoint_state(MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
# 为了提高效率,调用线程协调器
coord = tf.train.Coordinator()####
threads = tf.train.start_queue_runners(sess=sess, coord=coord)####
for i in range(STEPS):
# xs, ys = mnist.train.next_batch(BATCH_SIZE)
xs, ys = sess.run([img_batch, label_batch])####
_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: xs, y_: ys})
if i % 1000 == 0:
print("AFTER %d training step(s), loss on training batch is %g" % (i, loss_value))
saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)
coord.request_stop()####
coord.join(threads)####
def main():
mnist = input_data.read_data_sets('data', one_hot=True)
backward(mnist)
if __name__ == '__main__':
main()
test.py
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
## 为了延迟导入time模块
import time
import forward
import backward
import generateds
TEST_INTERVAL_SECS = 5
TEST_NUM = 10000####
def test(mnist):
# 复现计算图
with tf.Graph().as_default() as g:
# 定义x y_ y
x = tf.placeholder(tf.float32, [None, forward.INPUT_MODE])
y_ = tf.placeholder(tf.float32, [None, forward.OUTPUT_MODE])
y = forward.forward(x, None)
## 实例化可还原滑动平均值的saver
ema = tf.train.ExponentialMovingAverage(backward.MOVING_AVERAGE_DECAY)
ema_restore = ema.variables_to_restore()
saver = tf.train.Saver(ema_restore)
correct_prediction = tf.equal(tf.argmax(y_, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
img_batch, label_batch = generateds.get_tfRecord(TEST_NUM, isTrain=False)####
# 计算正确率
while True:
with tf.Session() as sess:
# 加载ckpt模型
ckpt = tf.train.get_checkpoint_state(backward.MODEL_SAVE_PATH)
# 如果已有ckpt模型则恢复
if ckpt and ckpt.model_checkpoint_path:
# 恢复会话
saver.restore(sess, ckpt.model_checkpoint_path)
# 恢复轮数
global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
coord = tf.train.Coordinator()####
threads = tf.train.start_queue_runners(sess=sess, coord=coord)####
xs, ys = sess.run([img_batch, label_batch])####
# 计算准确率
accuracy_score = sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels})
# 打印提示
print("After %s training step(s), test accuracy = %g" % (global_step, accuracy_score))
coord.request_stop()####
coord.join(threads)####
else:
print("No checkpoint file found")
return
time.sleep(TEST_INTERVAL_SECS)
def main():
mnist = input_data.read_data_sets('data', one_hot=True)
test(mnist)
if __name__ == '__main__':
main()
app.py
import tensorflow as tf
import numpy as np
from PIL import Image
import forward
import backward
def pre_pic(picName):
img = Image.open(picName)
reIm = img.resize((28, 28), Image.ANTIALIAS)
im_arr = np.array(reIm.convert('L')) # 变成灰度图
"""
模型要求的是黑底白字
输入的图片是白底黑字
因此要给输入图片反色
纯白色255
"""
threshold = 50
for i in range(28):
for j in range(28):
im_arr[i][j] = 255 - im_arr[i][j]
if (im_arr[i][j] < threshold):
im_arr[i][j] = 0
else:
im_arr[i][j] = 255
nm_arr = im_arr.reshape([1, 784])
nm_arr = nm_arr.astype(np.float32)
img_ready = np.multiply(nm_arr, 1.0/255.0)
return img_ready
def restore_model(testPicArr):
with tf.Graph().as_default() as tg:
# 仅需要给输入x占位
x = tf.placeholder(tf.float32, [None, forward.INPUT_MODE])
# 计算求得输出y
y = forward.forward(x, None)
# 返回预测结果索引
preValue = tf.argmax(y, 1)
# 实例化带有滑动平均值的saver
variable_averages = tf.train.ExponentialMovingAverage(backward.MOVING_AVERAGE_DECAY)
variable_to_restore = variable_averages.variables_to_restore() ####
saver = tf.train.Saver(variable_to_restore)
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(backward.MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
preValue = sess.run(preValue, feed_dict={x:testPicArr})
return preValue
else:
print("No checkpoint file found")
return -1
def application():
testNum = int(input("input the number of test pictures:"))
for i in range(testNum):
testPic = input("the path of test picture")
testPicArr = pre_pic(testPic)
preValue = restore_model(testPicArr)
print("The prediction number is: ", preValue)
def main():
application()
if __name__ == '__main__':
main()