TensorFlow图像预处理完整案例

本节，通过将训练图像进行预处理，训练得到的神经网络模型可以识别不同大小、方位、色彩等方面的实体。

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

# 随机调整图片的色彩、定义两种顺序
def distort_color(image, color_ordering=0):
    if color_ordering == 0:
        image = tf.image.random_brightness(image, max_delta=32./255.)
        image = tf.image.random_saturation(image, lower=0.5, upper=1.5)
        image = tf.image.random_hue(image, max_delta=0.2)
        image = tf.image.random_contrast(image, lower=0.5, upper=1.5)
    else:
        image = tf.image.random_saturation(image, lower=0.5, upper=1.5)
        image = tf.image.random_brightness(image, max_delta=32./255.)
        image = tf.image.random_contrast(image, lower=0.5, upper=1.5)
        image = tf.image.random_hue(image, max_delta=0.2)

    return tf.clip_by_value(image, 0.0, 1.0)


# 对图片进行预处理，将图片转换成神经网络的输入层数据
def preprocess_for_train(image, height, width, bbox):
    # 查看是否存在标注框。
    if bbox is None:
        bbox = 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)
        
    # 随机的截取图片中一个块。
    bbox_begin, bbox_size, _ = tf.image.sample_distorted_bounding_box(
        tf.shape(image), bounding_boxes=bbox)
    bbox_begin, bbox_size, _ = tf.image.sample_distorted_bounding_box(
        tf.shape(image), bounding_boxes=bbox)
    distorted_image = tf.slice(image, bbox_begin, bbox_size)

    # 将随机截取的图片调整为神经网络输入层的大小。
    distorted_image = tf.image.resize_images(distorted_image, [height, width], method=np.random.randint(4))
    distorted_image = tf.image.random_flip_left_right(distorted_image)
    distorted_image = distort_color(distorted_image, np.random.randint(2))
    return distorted_image.


# 读取图片
image_raw_data = tf.gfile.FastGFile("../../datasets/cat.jpg", "r").read()
with tf.Session() as sess:
    img_data = tf.image.decode_jpeg(image_raw_data)
    boxes = tf.constant([[[0.05, 0.05, 0.9, 0.7], [0.35, 0.47, 0.5, 0.56]]])
    for i in range(9):
        result = preprocess_for_train(img_data, 299, 299, boxes)
        plt.imshow(result.eval())
        plt.show()

结果展示：

 

参考：TensorFlow：实战Google深度学习框架