python频繁写入文件时提速的方法

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

import numpy as np

from glob import glob

import math

import os

import torch

from tqdm import tqdm

import multiprocessing

label_path = '/home/ying/data/shiyongjie/distortion_datasets/new_distortion_dataset/train/label.txt'

file_path = '/home/ying/data/shiyongjie/distortion_datasets/new_distortion_dataset/train/distortion_image'

save_path = '/home/ying/data/shiyongjie/distortion_datasets/new_distortion_dataset/train/flow_field'

r_d_max = 128

image_index = 0

txt_file = open(label_path)

file_list = txt_file.readlines()

txt_file.close()

file_label = {}

for i in file_list:

  i = i.split()

  file_label[i[0]] = i[1]

r_d_max = 128

eps = 1e-32

H = 256

W = 256

def generate_flow_field(image_list):

  for image_file_path in ((image_list)):

    pixel_flow = np.zeros(shape=tuple([256, 256, 2])) # 按照pytorch中的grid来写

    image_file_name = os.path.basename(image_file_path)

    # print(image_file_name)

    k = float(file_label[image_file_name])*(-1)*1e-7

    # print(k)

    r_u_max = r_d_max/(1+k*r_d_max**2) # 计算出畸变校正之后的对角线的理论长度

    scale = r_u_max/128 # 将这个长度压缩到256的尺寸，会有一个scale，实际上这里写128*sqrt(2)可能会更加直观

    for i_u in range(256):

      for j_u in range(256):

        x_u = float(i_u - 128)

        y_u = float(128 - j_u)

        theta = math.atan2(y_u, x_u)

        r = math.sqrt(x_u ** 2 + y_u ** 2)

        r = r * scale # 实际上得到的r，即没有resize到256×256的图像尺寸size，并且带入公式中

        r_d = (1.0 - math.sqrt(1 - 4.0 * k * r ** 2)) / (2 * k * r + eps) # 对应在原图（畸变图）中的r

        x_d = int(round(r_d * math.cos(theta)))

        y_d = int(round(r_d * math.sin(theta)))

        i_d = int(x_d + W / 2.0)

        j_d = int(H / 2.0 - y_d)

        if i_d < W and i_d >= 0 and j_d < H and j_d >= 0: # 只有求的的畸变点在原图中的时候才进行赋值

          value1 = (i_d - 128.0)/128.0

          value2 = (j_d - 128.0)/128.0

          pixel_flow[j_u, i_u, 0] = value1 # mesh中存储的是对应的r的比值，在进行畸变校正的时候，给定一张这样的图，进行找像素即可

          pixel_flow[j_u, i_u, 1] = value2

# 保存成array格式

    saved_image_file_path = os.path.join(save_path, image_file_name.split('.')[0] + '.npy')

    pixel_flow = pixel_flow.astype('f2') # 将数据的格式转换成float16类型， 节省空间

    # print(saved_image_file_path)

    # print(pixel_flow)

    np.save(saved_image_file_path, pixel_flow)

  return

if __name__ == '__main__':

  file_list = glob(file_path + '/*.JPEG')

  m = 32

  n = int(math.ceil(len(file_list) / float(m))) # 向上取整

  result = []

  pool = multiprocessing.Pool(processes=m) # 32进程

  for i in range(0, len(file_list), n):

    result.append(pool.apply_async(generate_flow_field, (file_list[i: i+n],)))

  pool.close()

  pool.join()
          

            
if __name__ == '__main__':

  file_list = glob(file_path + '/*.JPEG') # 将文件夹下所有的JPEG文件列成一个list

  m = 32 # 假设CPU有32个核心

  n = int(math.ceil(len(file_list) / float(m))) # 每一个核心需要处理的list的数目

  result = []

  pool = multiprocessing.Pool(processes=m) # 开32线程的线程池

  for i in range(0, len(file_list), n):

    result.append(pool.apply_async(generate_flow_field, (file_list[i: i+n],))) # 对每一个list都用上面我们定义的函数进行处理

  pool.close() # 处理结束之后，关闭线程池

  pool.join()
          

            
pool = multiprocessing.Pool(processes=m) # 开32线程的线程池
          

            
result.append(pool.apply_async(generate_flow_field, (file_list[i: i+n],))) # 对每一个list都用上面我们定义的函数进行处理
          

            
f = open('blogCblog.txt', 'w') #首先先创建一个文件对象，打开方式为w
f.writelines('123456') #用readlines()方法写入文件
          

            
f = open('blogCblog.txt', 'w') #首先先创建一个文件对象，打开方式为w
f.writelines(123456) #用readlines()方法写入文件