自制做数据集的手写数字识别的神经网络实践
经过一番训练之后发现识别的准确率已经达到98%，可是在实际的运行过程中，数字5还是识别成了3，不知道是不是哪里的代码写错了。但是其他数字还是非常准确的识别出来了。下面来看看结果。
上面的实践结果代码如下的几个类所示。因为这个实践需要6万张的训练图片和1万张的测试图片来训练，详细的代码可以从这里下载到。https://code.5288z.com/zhangyuqing/AIPractice
#coding:utf-8
#fc4_mnist_generateds.py
#本文件主要为生成数据集的文件,生成训练和测试的数据图片集合
import tensorflow as tf
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 write_tfRecord(tfRecordName,image_path,label_path):
writer = tf.python_io.TFRecordWriter(tfRecordName)
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 "writer tfRecord successful"
def generate_tfRecord():
isExists = os.path.exists(data_path)
if not isExists:
os.mkdir(data_path)
print "the directory was created successful"
else:
print "the directory already exists"
write_tfRecord(tfRecord_train,image_train_path,label_train_path)
write_tfRecord(tfRecord_test,image_test_path,label_test_path)
def read_tfRecord(tfRecord_path):
filename_queue = tf.train.string_input_producer([tfRecord_path],shuffle=True)
reader = tf.TFRecordReader()
_,serialized_example = reader.read(filename_queue)
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) * (1.0/255)
label = tf.cast(features['label'],tf.float32)
return img,label
def get_tfrecord(num,isTrain=True):
if isTrain:
tfRecord_path = tfRecord_train
else:
tfRecord_path = tfRecord_test
img,label = read_tfRecord(tfRecord_path)
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 main():
generate_tfRecord()
if __name__ == '__main__':
main()#coding=utf-8
#fc4_mnist_forward.py
import tensorflow as tf
INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500
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
def forward(x,regularizer):
w1 = get_weight([INPUT_NODE,LAYER1_NODE],regularizer)
b1 = get_bias([LAYER1_NODE])
y1 = tf.nn.relu(tf.matmul(x,w1) + b1)
w2 = get_weight([LAYER1_NODE,OUTPUT_NODE],regularizer)
b2 = get_bias([OUTPUT_NODE])
y = tf.matmul(y1,w2) + b2
return y
if __name__ == '__main__':
print 'this is the main method'#coding=utf-8
#fc4_mnist_backward.py
import tensorflow as tf
import os
import fc4_mnist_generateds
import fc4_mnist_forward
BATCH_SIZE = 200
LEARNING_REATE_BASE = 0.1
LARNING_REATE_DECAY = 0.99
REGULARIZER = 0.0001
STEPS = 50000
MOVING_AVERAGE_DECAY = 0.99
MODEL_SAVE_PATH = "./model/"
MODEL_NAME = "mnist_model"
train_num_examples = 60000
def backward():
x = tf.placeholder(tf.float32,[None,fc4_mnist_forward.INPUT_NODE])
y_ = tf.placeholder(tf.float32,[None,fc4_mnist_forward.OUTPUT_NODE])
y = fc4_mnist_forward.forward(x,REGULARIZER)
global_step = tf.Variable(0,trainable=False)
ce = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y,labels=tf.argmax(y_,1))
cem = tf.reduce_mean(ce)
loss = cem + tf.add_n(tf.get_collection('losses'))
leaning_rate = tf.train.exponential_decay(
LEARNING_REATE_BASE,
global_step,
train_num_examples / BATCH_SIZE,
LARNING_REATE_DECAY,
staircase=True
)
train_step = tf.train.GradientDescentOptimizer(leaning_rate).minimize(loss,global_step=global_step)
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 = fc4_mnist_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)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess,coord=coord)
for i in range(STEPS):
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 steps, loss on training batch is %g" %(step,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():
backward()
if __name__ == '__main__':
main()# coding:utf-8
# fc4_mnist_test.py
import time
import tensorflow as tf
import fc4_mnist_backward
import fc4_mnist_generateds
import fc4_mnist_forward
TEST_INTERVAL_SECS = 5
TEST_NUM = 10000
def test():
with tf.Graph().as_default() as g:
x = tf.placeholder(tf.float32, [None, fc4_mnist_forward.INPUT_NODE])
y_ = tf.placeholder(tf.float32, [None, fc4_mnist_forward.OUTPUT_NODE])
y = fc4_mnist_forward.forward(x, None)
ema = tf.train.ExponentialMovingAverage(fc4_mnist_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 = fc4_mnist_generateds.get_tfrecord(TEST_NUM, isTrain=False)
while True:
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(fc4_mnist_backward.MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
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])
accuracy_score = sess.run(accuracy, feed_dict={x: xs, y_: ys})
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():
test()
if __name__ == '__main__':
main()
# coding:utf-8
#fc4_mnist_app.py
import tensorflow as tf
import numpy as np
from PIL import Image
import fc4_mnist_backward
import fc4_mnist_forward
def restore_model(testPicArr):
with tf.Graph().as_default() as tg:
x = tf.placeholder(tf.float32, [None,fc4_mnist_forward.INPUT_NODE])
y = fc4_mnist_forward.forward(x, None)
preValue = tf.argmax(y, 1)
variable_averages = tf.train.ExponentialMovingAverage(fc4_mnist_backward.MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(fc4_mnist_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 pre_pic(picName):
img = Image.open(picName)
reIm = img.resize((28, 28), Image.ANTIALIAS)
im_arr = np.array(reIm.convert('L'))
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 = np.multiply(nm_arr, 1.0 / 255.0)
return nm_arr # img
def application():
testNum = input("input the number of test pictures:")
for i in range(testNum):
testPic = raw_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()
