仅使用 tensorflow 进行训练中的数据扩充

Question

我想做一些随机增强，只在火车时间。

我已将扩充合并为图表的一部分 - 我认为这是一种错误，因为同一张图表也用于测试 - 我不希望测试图像被扩充。

x = tf.placeholder(tf.float32, shape=[None, _IMAGE_SIZE * _IMAGE_SIZE * _IMAGE_CHANNELS], name='Input')
y = tf.placeholder(tf.float32, shape=[None, _NUM_CLASSES], name='Output')

#reshape the input so we can apply conv2d########
x_image = tf.reshape(x, [-1,32,32,3])


x_image = tf.map_fn(lambda frame: tf.random_crop(frame, [_IMAGE_SIZE, _IMAGE_SIZE, _IMAGE_CHANNELS]), x_image)
x_image = tf.map_fn(lambda frame: tf.image.random_flip_left_right(frame), x_image)
x_image = tf.map_fn(lambda frame: tf.image.random_brightness(frame, max_delta=63), x_image)
x_image = tf.map_fn(lambda frame: tf.image.random_contrast(frame, lower=0.2, upper=1.8), x_image)
x_image = tf.map_fn(lambda frame: tf.image.per_image_standardization(frame), x_image)

我希望仅在测试时应用上述增强 - 如何实现？

Answer 1

解决这个问题很简单

def pre_process_image(image, training):
if training:
    Do things
else:
    Do some other things
return image


def pre_process(images, training):
    images = tf.map_fn(lambda image: pre_process_image(image, training), images)
    return images

然后根据需要在模型中调用pre_process

if is_training == True:
    with tf.variable_scope('augment', reuse=False):
        with tf.device('/cpu:0'):
            x_image = tf.reshape(x, [-1, _IMAGE_SIZE, _IMAGE_SIZE, _IMAGE_CHANNELS], name='images')
            x_image = pre_process(x_image, is_training)
else:

    with tf.variable_scope('augment', reuse=True):
        with tf.device('/cpu:0'):
            x_image = tf.reshape(x, [-1, _IMAGE_SIZE, _IMAGE_SIZE, _IMAGE_CHANNELS], name='images')
            x_image = pre_process(x_image, is_training)

仅使用 tensorflow 进行训练中的数据扩充

Data augmentation in training only with tensorflow

conv-neural-network

tensorflow

data-augmentation