Emmahuu424的博客

https://zlearning.netlify.app/computer/prml/prmlch1dot1-polynomial-curve

https://shimo.im/docs/TKxJPTTXvv3KD9Yr/

【转载】https://www.huaweicloud.com/articles/1bbc978269862843879e580761883927.html

https://www.jiqizhixin.com/articles/2018-04-23-3

（1）调节尺寸As data(Images) few into the NN should be scaled according the image size that the NN is designed to take, usually a square i.e 100x100,250x250（2） 特征标准化（Feature Standardization）特征标准化（Feature Standardization）特征标准化的目的是使数据集中所有特征都具有零均值和单位方差，即数据的每一个

【转载】https://niuyuanyuanna.github.io/2018/11/08/deep_learning/data-normalization/#%E9%80%90%E6%A0%B7%E6%9C%AC%E5%9D%87%E5%80%BC%E6%B6%88%E5%87%8Fper-example-mean-subtraction

https://segmentfault.com/a/1190000024535003

【转载】https://bbs.cvmart.net/topics/3420

【转载】https://my.oschina.net/u/4218785/blog/4699354

dst参数的含义dst => destination，生成目标。方法一：可以通过自定义变量获取，如：img = cv2.blur(src, kernel, …)方法二：可以直接调用函数，并指定应用的目标raw，如：raw = img.copy()cv2.blur(src, kernel, raw…)Example# -*- coding:utf-8 -*-...

# -*- coding:utf-8 -*-#@Time: 2020/2/18#@Author: EmmaHuu#@File: gauss_noise"""添加高斯噪声Gauss Noise """import cv2 as cvimport numpy as npdef gauss_noise(img,sigma): temp_img = np.float64(np.cop...