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:
- 输入输出图像时一定要使用uint8编码,
- 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 width: 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()
时间: 2024-10-13 15:51:13