图像重建生成领域指标之Sharpness Difference

该指标在2016年的leCun的一篇文章中有详细的解释，https://arxiv.org/abs/1511.05440

更多的指标：https://blog.csdn.net/hacker_long/article/details/104509523

具体的实现方式：

import numpy as np
import os
import cv2
import tensorflow as tf
from tensorflow.keras import layers
import tensorflow.compat.v1 as tf1
tf1.disable_v2_behavior()
def log10(t):
    """
    Calculates the base-10 log of each element in t.
    @param t: The tensor from which to calculate the base-10 log.
    @return: A tensor with the base-10 log of each element in t.
    """

    numerator = tf1.log(t)
    denominator = tf1.log(tf.constant(10, dtype=numerator.dtype))
    return numerator / denominator
def sharp_diff_error(gen_frames, gt_frames):
    """
    Computes the Sharpness Difference error between the generated images and the ground truth
    images.
    @param gen_frames: A tensor of shape [batch_size, height, width, 3]. The frames generated by the
                       generator model.
    @param gt_frames: A tensor of shape [batch_size, height, width, 3]. The ground-truth frames for
                      each frame in gen_frames.
    @return: A scalar tensor. The Sharpness Difference error over each frame in the batch.
    """
    gen_frames = tf1.to_float(gen_frames) / 255
    gt_frames = tf1.to_float(gt_frames) / 255
    shape = tf.shape(gen_frames)
    num_pixels = tf1.to_float(shape[1] * shape[2] * shape[3])

    # gradient difference
    # create filters [-1, 1] and [[1],[-1]] for diffing to the left and down respectively.
    # TODO: Could this be simplified with one filter [[-1, 2], [0, -1]]?
    pos = tf.constant(np.identity(3), dtype=tf.float32)
    neg = -1 * pos
    filter_x = tf.expand_dims(tf.stack([neg, pos]), 0)  # #[1, 2, 3, 3]
    filter_y = tf.stack([tf.expand_dims(pos, 0), tf.expand_dims(neg, 0)])  # #[2,1,3,3]
    strides = [1, 1, 1, 1]  # stride of (1, 1)
    padding = 'SAME'

    gen_dx = tf.abs(tf.nn.conv2d(gen_frames, filter_x, strides, padding=padding))
    gen_dy = tf.abs(tf.nn.conv2d(gen_frames, filter_y, strides, padding=padding))
    gt_dx = tf.abs(tf.nn.conv2d(gt_frames, filter_x, strides, padding=padding))
    gt_dy = tf.abs(tf.nn.conv2d(gt_frames, filter_y, strides, padding=padding))

    gen_grad_sum = gen_dx + gen_dy
    gt_grad_sum = gt_dx + gt_dy

    grad_diff = tf.abs(gt_grad_sum - gen_grad_sum)

    batch_errors = 10 * log10(1 / ((1 / num_pixels) * tf.reduce_sum(grad_diff, [1, 2, 3])))
    return tf.reduce_mean(batch_errors)

if __name__ == "__main__":
    ori_path = 'xxx.jpg'
    recon_path = 'xxx.png'
    batch_ori_img = []
    batch_recon_img = []
    ori_img = cv2.resize(cv2.imread(ori_path), (616, 112))
    recon_img = cv2.resize(cv2.imread(recon_path), (616, 112))
    print(ori_img.shape)
    batch_ori_img.append(ori_img)
    batch_recon_img.append(recon_img)
    batch_ori_img_n = np.array(batch_ori_img)
    batch_recon_img_n = np.array(batch_recon_img)
    print(batch_recon_img_n.shape)
    sd = sharp_diff_error(batch_recon_img_n, batch_ori_img_n)
    sess = tf1.Session()
    sd_ = sess.run(sd)
    print(sd_)

值得注意的是：这里比较巧妙的通过设计卷积核的参数，通过使用卷积来实现图像列于列间，行与行间的作差，其中filter_x的尺寸为[1,2,3,3], filter_y的尺寸为[2,1,3,3]，分别对应filter的height，width， in_channel和out_channel。

详细原理大家可以参考tf.nn.conv2d的用法。

PS：PSNR和SSIM的计算pandas都提供了成熟的方法可直接调用