python图片处理（去重，缩放）

1.python文件夹下图片去重(参考删除重复文件或图片（去重）的python代码)

# /usr/bin/env python
# -*- coding:utf-8 -*-
# 运行的代码文件要放到删除重复的文件或图片所包含的目录中
import os
import hashlib

filedir = '/home/xx/xx/xx'
def filecount(DIR):
    filecount = len([name for name in os.listdir(DIR) if os.path.isfile(os.path.join(DIR, name))])
    return (filecount)


def md5sum(filename):
    f = open(filedir+'/'+filename, 'rb')
    md5 = hashlib.md5()
    while True:
        fb = f.read(8096)
        if not fb:
            break
        md5.update(fb)
    f.close()
    return (md5.hexdigest())


def delfile():
    all_md5 = {}
    dir =os.walk(filedir)
    for i in dir:
        for tlie in i[2]:

            if md5sum(tlie) in all_md5.values():
                os.remove(filedir+'/'+tlie)
                print(tlie)
            else:
                all_md5[tlie] = md5sum(tlie)


if __name__ == '__main__':
    oldf = filecount(filedir)
    print('去重前有', oldf, '个文件
请稍等正在删除重复文件...')
    delfile()
    print('

去重后剩', filecount(filedir), '个文件')
    print('

一共删除了', oldf - filecount(filedir), '个文件

')

2.图片批量修改为同一尺寸（参考：https://www.cnblogs.com/neo-T/p/6477378.html）

# -*- coding: utf-8 -*-

import os
import cv2

IMAGE_SIZE = 256


# 按照指定图像大小调整尺寸
def resize_image(image, height=IMAGE_SIZE, width=IMAGE_SIZE):
    top, bottom, left, right = (0, 0, 0, 0)

    # 获取图像尺寸
    h, w, _ = image.shape

    # 对于长宽不相等的图片，找到最长的一边
    longest_edge = max(h, w)

    # 计算短边需要增加多上像素宽度使其与长边等长
    if h < longest_edge:
        dh = longest_edge - h
        top = dh // 2
        bottom = dh - top
    elif w < longest_edge:
        dw = longest_edge - w
        left = dw // 2
        right = dw - left
    else:
        pass

        # RGB颜色
    BLACK = [0, 0, 0]

    # 给图像增加边界，是图片长、宽等长，cv2.BORDER_CONSTANT指定边界颜色由value指定
    constant = cv2.copyMakeBorder(image, top, bottom, left, right, cv2.BORDER_CONSTANT, value=BLACK)

    # 调整图像大小并返回
    return cv2.resize(constant, (height, width))


# 读取训练数据
images = []
labels = []


def read_path(path_name):
    for dir_item in os.listdir(path_name):
        print(dir_item)
        # 从初始路径开始叠加，合并成可识别的操作路径
        full_path = os.path.abspath(os.path.join(path_name, dir_item))
        # print(full_path)
        if os.path.isdir(full_path):  # 如果是文件夹，继续递归调用
            read_path(full_path)
        else:  # 文件
            if dir_item.endswith('.jpg'):
                image = cv2.imread(full_path)
                image = resize_image(image, IMAGE_SIZE, IMAGE_SIZE)
                cv2.imwrite(full_path, image)
                print(dir_item)






if __name__ == '__main__':
    read_path('/home/xx/xx/xx')

list去重

1.

a=[1,2,3,1,5,1,6]
print(list(set(a)))

2.

a=[[1,2],[5,6],[1,2]]
b=[tuple(x) for x in a ]
c=[list(x) for x in set(b)]
print(c)