• 『TensorFlow』第九弹_图像预处理_不爱红妆爱武装


    部分代码单独测试:

    这里实践了图像大小调整的代码,值得注意的是格式问题:

    1. 输入输出图像时一定要使用uint8编码,
    2. 但是数据处理过程中TF会自动把编码方式调整为float32,所以输入时没问题,输出时要手动转换回来!使用numpy.asarray(dtype)或者tf.image.convert_image_dtype(dtype)都行
    都行 1 import numpy as np
     2 import tensorflow as tf
     3 import matplotlib.pyplot as plt
     4 
     5 # 使用'r'会出错,无法解码,只能以2进制形式读取
     6 # img_raw = tf.gfile.FastGFile('./123.png','rb').read()
     7 img_raw = open('./123.png','rb').read()
     8 
     9 # 把二进制文件解码为uint8
    10 img_0 = tf.image.decode_png(img_raw)
    11 # 不太必要了,可以用np直接转换了
    12 # img_1 = tf.image.convert_image_dtype(img_0,dtype=tf.uint8)
    13 
    14 sess = tf.Session()
    15 print(sess.run(img_0).shape)
    16 # plt.imshow(sess.run(img_0))
    17 # plt.show()
    18 
    19 def show_pho(img,sess=sess):
    20     '''
    21     TF处理过的图片自动转换了类型,需要调整回uint8才能正常显示
    22     :param sess: 
    23     :param img: 
    24     :return: 
    25     '''
    26     cat = np.asarray(sess.run(img),dtype='uint8')
    27     print(cat.shape)
    28     plt.imshow(cat)
    29     plt.show()
    30 
    31 
    32 '''调整图像大小'''
    33 # 插值尽量保存原图信息
    34 img_1 = tf.image.resize_images(img_0,[500,500],method=3)
    35 # show_pho(img_1)
    36 
    37 # 裁剪或填充
    38 # 自动中央截取
    39 img_2 = tf.image.resize_image_with_crop_or_pad(img_0,500,500)
    40 # show_pho(img_2)
    41 # 自动四周填充[0,0,0]
    42 img_3 = tf.image.resize_image_with_crop_or_pad(img_0,2500,2500)
    43 # show_pho(sess,img_3)
    44 
    45 # 比例中央裁剪
    46 img_4 = tf.image.central_crop(img_0,0.5)
    47 # show_pho(img_4)
    48 
    49 # 画框裁剪
    50 # {起点高度,起点宽度,框高,框宽}
    51 img_5 = tf.image.crop_to_bounding_box(img_0,700,300,500,500)
    52 show_pho(img_5)

    完整的图像预处理函数:

    处理单张图片

     1 import tensorflow as tf
     2 import numpy as np
     3 # import matplotlib.pyplot as plt
     4 
     5 def distort_color(image, color_ordering=0):
     6     '''
     7     随机调整图片的色彩,定义两种处理顺序。
     8     注意,对3通道图像正常,4通道图像会出错,自行先reshape之
     9     :param image: 
    10     :param color_ordering: 
    11     :return: 
    12     '''
    13     if color_ordering == 0:
    14         image = tf.image.random_brightness(image, max_delta=32./255.)
    15         image = tf.image.random_saturation(image, lower=0.5, upper=1.5)
    16         image = tf.image.random_hue(image, max_delta=0.2)
    17         image = tf.image.random_contrast(image, lower=0.5, upper=1.5)
    18     else:
    19         image = tf.image.random_saturation(image, lower=0.5, upper=1.5)
    20         image = tf.image.random_brightness(image, max_delta=32./255.)
    21         image = tf.image.random_contrast(image, lower=0.5, upper=1.5)
    22         image = tf.image.random_hue(image, max_delta=0.2)
    23 
    24     return tf.clip_by_value(image, 0.0, 1.0)
    25 
    26 
    27 def preprocess_for_train(image, height, width, bbox):
    28     '''
    29     对图片进行预处理,将图片转化成神经网络的输入层数据。
    30     :param image: 
    31     :param height: 
    32     :param  
    33     :param bbox: 
    34     :return: 
    35     '''
    36     # 查看是否存在标注框。
    37     if image.dtype != tf.float32:
    38         image = tf.image.convert_image_dtype(image, dtype=tf.float32)
    39 
    40     # 随机的截取图片中一个块。
    41     bbox_begin, bbox_size, _ = tf.image.sample_distorted_bounding_box(
    42         tf.shape(image), bounding_boxes=bbox)
    43     bbox_begin, bbox_size, _ = tf.image.sample_distorted_bounding_box(
    44         tf.shape(image), bounding_boxes=bbox)
    45     distorted_image = tf.slice(image, bbox_begin, bbox_size)
    46 
    47     # 将随机截取的图片调整为神经网络输入层的大小。
    48     distorted_image = tf.image.resize_images(distorted_image, [height, width], method=np.random.randint(4))
    49     distorted_image = tf.image.random_flip_left_right(distorted_image)
    50     distorted_image = distort_color(distorted_image, np.random.randint(2))
    51     return distorted_image
    52 
    53 def pre_main(img,bbox=None):
    54     if bbox is None:
    55         bbox = tf.constant([0.0, 0.0, 1.0, 1.0], dtype=tf.float32, shape=[1, 1, 4])
    56     with tf.gfile.FastGFile(img, "rb") as f:
    57         image_raw_data = f.read()
    58     with tf.Session() as sess:
    59         img_data = tf.image.decode_jpeg(image_raw_data)
    60         for i in range(9):
    61             result = preprocess_for_train(img_data, 299, 299, bbox)
    62             # {wb打开文件{矩阵编码为jpeg{格式转换为uint8}}.eval()}
    63             with tf.gfile.FastGFile('./代号{}.jpeg'.format(i),'wb') as f:
    64                 f.write(sess.run(tf.image.encode_jpeg(tf.image.convert_image_dtype(result,dtype=tf.uint8))))
    65             # plt.imshow(result.eval())
    66             # plt.axis('off')
    67             # plt.savefig('代号{}'.format(i))
    68 
    69 
    70 if __name__=='__main__':
    71     pre_main("./123123.jpeg",bbox=None)
    72     exit()

     

  • 相关阅读:
    detect——point_in_polygon
    4. 基于faro SDK 读取fls原始文件
    vs2010+qt4编译出现error LNK2001: 无法解析的外部符号 "public: virtual struct QMetaObject等错误
    Redhat下安装启动Hadoop
    Using Multiple Kinect v2 on one PC
    Development With Kinect .NET SDK (Part V) – Developing Application using Multiple Kinect Devices
    Utilize kinect to build 3D model
    大数据 pdf 电子书大全 百度云
    50 Incredible Examples of HDR Photography
    分形几何学
  • 原文地址:https://www.cnblogs.com/hellcat/p/6912341.html
Copyright © 2020-2023  润新知