x = tf.placeholder(tf.float32, [None, 3072])
y = tf.placeholder(tf.int64, [None])
x_image = tf.reshape(x, [-1, 3, 32, 32])
x_image = tf.transpose(x_image, perm=[0, 2, 3, 1])
data_aug_2 = tf.image.random_brightness(x_image, max_delta=63)
data_aug_1 = tf.image.random_flip_left_right(data_aug_2)
data_aug_3 = tf.image.random_contrast(data_aug_1, lower=0.2, upper=1.8)
老师，如上对x_image进行数据增强，在：tensorboard中x_image的值是不是应该赋为data_aug_3?,如下：
inputs_summary = tf.summary.image(‘x_image’, data_aug_3)
还是：
inputs_summary = tf.summary.image(‘x_image’, x_image)
呀？