x, y = imageNumpyData()
state = np.random.get_state()
np.random.shuffle(x)
np.random.set_state(state)
np.random.shuffle(y)
# 打乱之后的x,y作为训练数据
x = np.array(x)
y = np.array(y)
import numpy as np
import tensorflow as tf
import os
from PIL import Image
import base64
import matplotlib.pyplot as plt
def imageNumpyData():
# the classification file root path
rootFilePath = './Data/'
rootAbsPath = os.path.abspath(rootFilePath)
node1FloderPath = os.listdir(rootAbsPath)
node1Path = [os.path.join(rootAbsPath, nodePath) for nodePath in node1FloderPath]
label = 0
imageLabel = []
imageData = []
for imagePath in node1Path:
display = 0
image = os.listdir(imagePath)
image = [os.path.join(imagePath, file) for file in image]
# 使用tensorflow
with tf.Session() as sess:
for image_raw in image:
try:
img = Image.open(image_raw)
if img.format == "BMP":
image_raw_data = tf.gfile.FastGFile(image_raw, 'rb').read()
image_data = tf.image.decode_bmp(image_raw_data)
if img.format == "JPEG":
image_raw_data = tf.gfile.FastGFile(image_raw, 'rb').read()
image_data = tf.image.decode_jpeg(image_raw_data)
if img.format == "PNG":
image_raw_data = tf.gfile.FastGFile(image_raw, 'rb').read()
image_data = tf.image.decode_png(image_raw_data)
if image_data.dtype != tf.float32:
image_data = tf.image.convert_image_dtype(image_data, dtype=tf.float32)
image_data = tf.image.resize_images(image_data, [224, 224])
image_temp = np.array(sess.run(image_data))
if image_temp.shape[2] == 1:
imageData.append(image_temp)
imageLabel.append(label)
display = display + 1
print(str(label) + ':' + str(display))
except:
print(image_raw + '读取失败')
# os.remove(image_raw)
label = label + 1
one_hot = tf.one_hot(imageLabel, label)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
imageLabel = sess.run(one_hot)
return imageData, imageLabel
def tfRecordWrite(filename):
# 生成整数的属性
def _int64_feature(value):
return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))
# 生成字符串型的属性
def _bytes_feature(value):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
# filename = 'record/Imageoutput.tfrecords'
writer = tf.python_io.TFRecordWriter(filename)
x, y = imageNumpyData()
state = np.random.get_state()
np.random.shuffle(x)
np.random.set_state(state)
np.random.shuffle(y)
# 打乱之后的x,y作为训练数据
x = np.array(x)
y = np.array(y)
# 将每张图片都转为一个Example
height = x.shape[1]
width = x.shape[2]
channels = x.shape[3]
n_class = y.shape[1]
x = x.reshape([-1, height, width, channels])
division = int(x.shape[0] * 0.9)
x_train = x[:division]
y_train = y[:division]
x_test = x[division:]
y_test = y[division:]
np.savez('testData.npz', test_X=x_test, test_Y=y_test, height=height, width=width, channels=channels,
n_class=n_class)
del x_test, y_test
for i in range(x_train.shape[0]):
image = x_train[i].tostring() # 将图像转为字符串
example = tf.train.Example(features=tf.train.Features(
feature={
'image': _bytes_feature(image),
'label': _int64_feature(np.argmax(y_train[i]))
}))
writer.write(example.SerializeToString()) # 将Example写入TFRecord文件
writer.close()
return height, width, channels, n_class
filename = r'./record\Imageoutput.tfrecords'
height, width, channels, n_class = tfRecordWrite(filename)
print(height, width, channels, n_class)
print('data processing success')
try:
img = Image.open(image_raw)
if img.format == "BMP":
image_raw_data = tf.gfile.FastGFile(image_raw, 'rb').read()
image_data = tf.image.decode_bmp(image_raw_data)
if img.format == "JPEG":
image_raw_data = tf.gfile.FastGFile(image_raw, 'rb').read()
image_data = tf.image.decode_jpeg(image_raw_data)
if img.format == "PNG":
image_raw_data = tf.gfile.FastGFile(image_raw, 'rb').read()
image_data = tf.image.decode_png(image_raw_data)
解释:尝试打开图片,并且图片格式是JPEG,BMP或PNG, tf.gfile.FastGFile的这个地方必须要‘rb’,我看一些书上仅仅是写了一个‘r’,这样并不对。
if image_data.dtype != tf.float32:
image_data = tf.image.convert_image_dtype(image_data, dtype=tf.float32)
解释:我做CNN的中,需要float32,这里必须转格式
image_data = tf.image.resize_images(image_data, [224, 224])
解释:把图片更改大小
if image_temp.shape[2] == 1:
imageData.append(image_temp)
imageLabel.append(label)
解释:我的是灰度图,所以这里**‘’==1‘’,若是三通道,则‘==3’**
one_hot = tf.one_hot(imageLabel, label)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
imageLabel = sess.run(one_hot)
解释:把得到的label,转换成one-hot形式
x = x.reshape([-1, height, width, channels])
division = int(x.shape[0] * 0.9)
x_train = x[:division]
y_train = y[:division]
x_test = x[division:]
y_test = y[division:]
np.savez('testData.npz', test_X=x_test, test_Y=y_test, height=height, width=width, channels=channels,
n_class=n_class)
del x_test, y_test
解释:这里是我拿出一部分数据保存成‘npz’的形式作为我的测试集,因为我用tfrecord格式的数据作为训练集
# 生成整数的属性
def _int64_feature(value):
return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))
# 生成字符串型的属性
def _bytes_feature(value):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
解释:这是我们必须遵从的规则,用整数属性写入label,用字符串形式写入图像数据
# filename = 'record/Imageoutput.tfrecords'
writer = tf.python_io.TFRecordWriter(filename)
解释:开始写入,并生成文件
for i in range(x_train.shape[0]):
image = x_train[i].tostring() # 将图像转为字符串
example = tf.train.Example(features=tf.train.Features(
feature={
'image': _bytes_feature(image),
'label': _int64_feature(np.argmax(y_train[i]))
}))
writer.write(example.SerializeToString()) # 将Example写入TFRecord文件
writer.close()
解释:根据数据集大小,一个一个的写入
数据集地址:
链接:https://pan.baidu.com/s/1aIHzKsxUb67sJZAFrGH1ZQ
提取码:lvjp
工程地址:
链接:https://pan.baidu.com/s/1XGAA6UQ0JByhvDYQ__my4g
提取码:dxpn