列举常见的几种数据集增强方法：
1.flip 翻折（左右，上下）
# NumPy.'img' = A single image. flip_1 = np.fliplr(img) # TensorFlow. 'x' = A placeholder for an image. shape = [height, width, channels] x = tf.placeholder(dtype = tf.float32, shape = shape) flip_2 = tf.image.flip_up_down(x) flip_3 = tf.image.flip_left_right(x) flip_4 = tf.image.random_flip_up_down(x) flip_5 = tf.image.random_flip_left_right(x)
2.rotation 旋转
# Placeholders: 'x' = A single image, 'y' = A batch of images # 'k' denotes the number of 90 degree anticlockwise rotations shape = [height, width, channels] x = tf.placeholder(dtype = tf.float32, shape = shape) rot_90 = tf.image.rot90(img, k=1) rot_180 = tf.image.rot90(img, k=2) # To rotate in any angle. In the example below, 'angles' is in radians shape = [batch, height, width, 3] y = tf.placeholder(dtype = tf.float32, shape = shape) rot_tf_180 = tf.contrib.image.rotate(y, angles=3.1415) # Scikit-Image. 'angle' = Degrees. 'img' = Input Image # For details about 'mode', checkout the interpolation section below. rot = skimage.transform.rotate(img, angle=45, mode='reflect')
3.scale 缩放
# Scikit Image. 'img' = Input Image, 'scale' = Scale factor # For details about 'mode', checkout the interpolation section below. scale_out = skimage.transform.rescale(img, scale=2.0, mode='constant') scale_in = skimage.transform.rescale(img, scale=0.5, mode='constant') # Don't forget to crop the images back to the original size (for # scale_out)
4.crop 裁剪
# TensorFlow. 'x' = A placeholder for an image. original_size = [height, width, channels] x = tf.placeholder(dtype = tf.float32, shape = original_size) # Use the following commands to perform random crops crop_size = [new_height, new_width, channels] seed = np.random.randint(1234) x = tf.random_crop(x, size = crop_size, seed = seed) output = tf.images.resize_images(x, size = original_size)
5.translation 水平或竖直移动
# pad_left, pad_right, pad_top, pad_bottom denote the pixel # displacement. Set one of them to the desired value and rest to 0 shape = [batch, height, width, channels] x = tf.placeholder(dtype = tf.float32, shape = shape) # We use two functions to get our desired augmentation x = tf.image.pad_to_bounding_box(x, pad_top, pad_left, height + pad_bottom + pad_top, width + pad_right + pad_left) output = tf.image.crop_to_bounding_box(x, pad_bottom, pad_right, height, width)
6.gaussion noise 噪点
#TensorFlow. 'x' = A placeholder for an image. shape = [height, width, channels] x = tf.placeholder(dtype = tf.float32, shape = shape) # Adding Gaussian noise noise = tf.random_normal(shape=tf.shape(x), mean=0.0, stddev=1.0, dtype=tf.float32) output = tf.add(x, noise)
7.gan高级增强
旋转、缩放等操作，有可能造成未知区域弥补，具体细节以及上面各种方法，见下面原文链接介绍。
源文：https://medium.com/nanonets/how-to-use-deep-learning-when-you-have-limited-data-part-2-data-augmentation-c26971dc8ced
译文：https://blog.csdn.net/u010801994/article/details/81914716