一、图片处理
1、图片存取 tf.gfile
import tensorflow as tf import matplotlib.pyplot as plt image_bytes = tf.gfile.FastGFile("dog.jpg", 'rb').read() # 字节 with tf.Session() as session: # 2.图片解码 img = tf.image.decode_jpeg(image_bytes) # print(img) # tensor('DecodePnng:0', shape=(?,?,?),dtype=uint8) img_array = img.eval() # 将tensor对象转成数组 # 3.图片显示 plt.imshow(img_array) plt.show() # 4.图片数据类型转化(整形) # img = tf.image.convert_image_dtype(img, dtype=tf.float32) # print(img) # 5.图像重编码 encode_image = tf.image.encode_jpeg(img) new_img = encode_image.eval() # 数组 # 6.图片保存 with tf.gfile.GFile("dog_new.png", "wb") as f: f.write(new_img)
2、图片修改 tf.image
import tensorflow as tf import matplotlib.pyplot as plt image_bytes = tf.gfile.FastGFile("dog.jpg", 'rb').read() # 字节 with tf.Session() as session: img = tf.image.decode_jpeg(image_bytes) # 翻转图片 img_flipped = tf.image.flip_up_down(img) # 上下反转 img_flipped = tf.image.flip_left_right(img_flipped) # 左右反转 img_flipped = tf.image.transpose_image(img_flipped) # 对角线反转 img_flipped = tf.image.random_flip_up_down(img_flipped) # 随机上下反转 img_flipped = tf.image.random_flip_left_right(img_flipped) # 随机左右反转 # 亮度设置 img_adjust = tf.image.adjust_brightness(img_flipped, -0.5) # 增加亮度 img_adjust = tf.image.adjust_brightness(img_adjust, +0.5) # 降低亮度 img_adjust = tf.image.random_brightness(img_adjust, max_delta=0.3) # 随机调整亮度，亮度在[-max_delta, +max_delta]] # 色度 img_saturation = tf.image.adjust_saturation(img_adjust, 1.5) # 支持random
# 饱和度 img_hue = tf.image.adjust_hue(img_saturation, delta=0.2)
# 对比度 img_contrast = tf.image.adjust_contrast(img_hue, 0.5) # 图片标准化 img_standard = tf.image.per_image_standardization(img_adjust) img_standard = tf.clip_by_value(img_standard, 0.0, 10) # 转成数组 img_array = img_standard.eval() plt.imshow(img_array) plt.show()
3、图像标注框
import tensorflow as tf import matplotlib.pyplot as plt image_bytes = tf.gfile.FastGFile("dog.jpg", 'rb').read() # 字节 with tf.Session() as session: img = tf.image.decode_jpeg(image_bytes) # 调整图片大小 img_resize = tf.image.resize_image_with_crop_or_pad(img, 300, 300) # 按比例截取图片 boxes = tf.constant([[[0.31, 0.22, 0.46, 0.38], [0.38, 0.53, 0.53, 0.71]]]) # 两个标注框 # boxes = tf.constant([[[0.31, 0.22, 0.46, 0.38]]]) # 设置一个RGB，设置四个角的比例位置 # 给原始图片添加一个图层 batched = tf.expand_dims(tf.image.convert_image_dtype(img_resize, tf.float32), 0) # 把boxes标注的框画到原始图片上 image_with_boxes = tf.image.draw_bounding_boxes(batched, boxes) # 重新将原始图片设置为RGB image_with_boxes = tf.reshape(image_with_boxes, [300, 300, 3]) img_array = image_with_boxes.eval() plt.imshow(img_array) plt.show()
4、图片随机截取
import matplotlib.pyplot as plt image_bytes = tf.gfile.FastGFile("dog.jpg", 'rb').read() # 字节 with tf.Session() as session: img = tf.image.decode_jpeg(image_bytes) # 给定截取框大小 bounding_boxes = tf.constant([[[0.31, 0.22, 0.46, 0.38]]]) # 设置一个RGB，设置四个角的比例位置 # 选择相关图像截取算法截图 # Bounding boxes are supplied and returned as `[y_min, x_min, y_max, x_max]`. begin, size, bboxes = tf.image.sample_distorted_bounding_box( tf.shape(img), bounding_boxes=bounding_boxes, min_object_covered=0.1 ) # 生成概要 # img_with_box = tf.image.draw_bounding_boxes(tf.expand_dims(tf.image.convert_image_dtype(img, dtype=tf.float32), 0), bboxes) # tf.summary.image('img_with_box', img_with_box) # print(begin.eval(), size.eval()) # 截图 distorted_img = tf.slice(img, begin, size) img_array = distorted_img.eval() plt.imshow(img_array) plt.show()
5、一个简单样例代码，实现随机截取图片
import tensorflow as tf import numpy as np import matplotlib.pyplot as plt class Sample: def load_jpg(self, path, mode='rb'): image_bytes = tf.gfile.FastGFile(path, mode).read() return tf.image.decode_jpeg(image_bytes, channels=3) def _distort_picture(self, image, color_ordering=0): if color_ordering == 0: image = tf.image.random_brightness(image, max_delta=32./255.) # 随机亮度 image = tf.image.random_contrast(image, lower=0.5, upper=1.5) # 对比度 image = tf.image.random_hue(image, max_delta=0.2) # 饱和度 image = tf.image.random_saturation(image, lower=0.5, upper=1.5)# 色度 if color_ordering == 1: image = tf.image.random_hue(image, max_delta=0.2) # 饱和度 image = tf.image.random_saturation(image, lower=0.5, upper=1.5)# 色度 image = tf.image.random_flip_left_right(image) image = tf.image.random_flip_up_down(image) return tf.clip_by_value(image, clip_value_min=0.0, clip_value_max=1.0) # 归一化 def _preprocess_for_train(self, image, height, width, bounding_boxes=None): if bounding_boxes is None: bounding_boxes = tf.constant([0.0, 0.0, 1.0, 1.0], dtype=tf.float32, shape=[1, 1, 4]) if image.dtype != tf.float32: image = tf.image.convert_image_dtype(image, dtype=tf.float32) begin, size, bboxes = tf.image.sample_distorted_bounding_box( tf.shape(image), bounding_boxes=bounding_boxes, min_object_covered=0.1 ) # 随机截图 distorted_image = tf.slice(image, begin=begin, size=size) # 调整随机截图的图片大小 # distorted_image = tf.image.resize_image_with_crop_or_pad(distorted_image, height, width) distorted_image = tf.image.resize_images( distorted_image, size=[height, width], method=np.random.randint(4) ) # 随机调整图片的一些设置 distorted_image = self._distort_picture(distorted_image, np.random.randint(2)) return distorted_image def get_random_picture(self, number, image, *args, **kwargs): with tf.Session() as session: for i in range(number): random_picture = self._preprocess_for_train(image, *args, **kwargs) plt.imshow(random_picture.eval()) plt.show() def main(): sample = Sample() image = sample.load_jpg("dog.jpg", 'rb') # bounding_boxes = tf.constant([0.2, 0.2, 0.8, 0.8], dtype=tf.float32, shape=[1, 1, 4]) bounding_boxes = tf.constant([[[0.2, 0.2, 0.8, 0.8]]]) height = width = 150 sample.get_random_picture(5, image, height, width, bounding_boxes) main()
5、图片处理有关函数整理
| 函数 | 描述 |
| tf.gfile.FastGFile | 读取单个图片，返回字节流数据 |
| tf.decode_jpeg | 在图片读入操作之后，图片处理之前，对图片进行解码 |
| tf.encode_jpeg | 在图片保存时对图片进行重编码 |
| tf.gfile.GFile | 写出单个图片 |
| tf.image.convert_image_dtype | 转换图片的数据类型 |
| tf.resize_images | 剪裁图片大小 |
| tf.resize_image_with_crop_of_pad | 剪裁单个图片大小 |
| tf.image.random_flip_left_right | 图片随机左右反转 |
| tf.image.random_flip_up_down | 图片随机上下反转 |
| tf.image.random_brightness | 图片随机调整亮度 |
| tf.image.random_hue | 图片随机调整饱和度 |
| tf.image.random_contrast | 图片随机调整对比度 |
| tf.image.random_saturation | 图片随机调整色度 |
| tf.image.per_image_standardization | 单个图片标准化 |
| tf.image.clip_by_value | 单个图片归一化，其它还有tf.image.clip_by_XXX等方法 |
| tf.expand_dims | 给图片增加维度(图层) |
| tf.image.sample_distorted_bounding_box | 生成随机子图 |
| tf.image.draw_bounding_boxes | 将标注框标注的子图取出来 |
| tf.image.reshape | 调整图片的维度 |
| tf.slice | 截取随机子图为单个图片 |
二、TFRecord
TFRecord文件是tensorflow指定的一种文件存储格式。它由tf.train.Example和tf.train.Feature来规定和实现。
# tf.train.Example Protocol Buffer
message Example {
Features features = 1; } message Features { map<string, Feature> feature = 1; } message Feature { oneof kind{ BytesList bytes_list = 1; FloatList float_list = 2; Int64List int64_list = 3; } }1、TFRecord文件写出
手写字mnist数据下载地址: http://yann.lecun.com/exdb/mnist/
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data import numpy as np # 导入训练集和测试集的图片和标签 mnist = input_data.read_data_sets("tensorflow/mnist/", dtype=tf.uint8, one_hot=True) # 获取图片和标签 images = mnist.train.images # images.shape (55000, 784) 热独编码 labels = mnist.train.labels # labels.shape (55000, 10) # 获取图像的数量及图片的分辨率([......]) numbers, pixels = images.shape # 按照tf.train.Example Protocol Buffer来定义TFRecord文件格式 def _int64(value): return tf.train.Feature(int64_list=tf.train.Int64List(value=[value])) def _bytes(value): return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value])) def example_protocol_buffer(pixel, size, image): example = tf.train.Example( features=tf.train.Features( feature={ 'pixels': _int64(pixels), 'label': _int64(size), 'image': _bytes(image) } ) ) return example.SerializeToString() # 序列化为字节 # 输出文件地址 filename = "tensorflow/test/mnist.tfrecord" # 创建一个writer writer = tf.python_io.TFRecordWriter(filename) # 遍历每张图片 for index in range(numbers): image = images[index].tostring() # 转成字节 serialize = example_protocol_buffer(pixels, np.argmax(labels[index]), image) writer.write(serialize) writer.close() print("done.")2、TFRecord文件读入
import tensorflow as tf
import matplotlib.pyplot as plt
# 创建reader reader = tf.TFRecordReader() # 创建字节流读取队列 filename_queue = tf.train.string_input_producer( ["tensorflow/test/mnist.tfrecord"] ) # 从文件中读取一个样例，read_up_to函数一次性读取多个样例 key, serialized_example = reader.read(filename_queue) # 解析读取的一个样例，如果需要解析多个样例，可以用parse_example def parse_single(serialized_example): features = tf.parse_single_example( serialized_example, features={ 'image': tf.FixedLenFeature([], tf.string), 'label': tf.FixedLenFeature([], tf.int64), 'pixels': tf.FixedLenFeature([], tf.int64) } ) # 将读取的单个样例解码 image = tf.decode_raw(features['image'], tf.uint8) label = tf.cast(features['label'], tf.int32) pixels = tf.cast(features['pixels'], tf.int32) return image, label, pixels sess = tf.Session() # 启动多线程处理输入数据 coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess=sess, coord=coord) for i in range(10): image, label, pixel = sess.run(parse_single(serialized_example)) print(image, label, pixel)
plt.imshow(image.reshape(28, 28))
plt.show()
