# -*-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來寫

    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) # 計算出畸變校正之后的對角線的理論長度

    scale = r_u_max/128 # 將這個長度壓縮到256的尺寸，會有一個scale，實際上這里寫128*sqrt(2)可能會更加直觀

    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 # 實際上得到的r，即沒有resize到256×256的圖像尺寸size，并且?guī)牍街?

        r_d = (1.0 - math.sqrt(1 - 4.0 * k * r ** 2)) / (2 * k * r + eps) # 對應在原圖（畸變圖）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: # 只有求的的畸變點在原圖中的時候才進行賦值

          value1 = (i_d - 128.0)/128.0

          value2 = (j_d - 128.0)/128.0

          pixel_flow[j_u, i_u, 0] = value1 # mesh中存儲的是對應的r的比值，在進行畸變校正的時候，給定一張這樣的圖，進行找像素即可

          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') # 將數(shù)據(jù)的格式轉換成float16類型， 節(jié)省空間

    # 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進程

  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') # 將文件夾下所有的JPEG文件列成一個list

  m = 32 # 假設CPU有32個核心

  n = int(math.ceil(len(file_list) / float(m))) # 每一個核心需要處理的list的數(shù)目

  result = []

  pool = multiprocessing.Pool(processes=m) # 開32線程的線程池

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

    result.append(pool.apply_async(generate_flow_field, (file_list[i: i+n],))) # 對每一個list都用上面我們定義的函數(shù)進行處理

  pool.close() # 處理結束之后，關閉線程池

  pool.join()

pool = multiprocessing.Pool(processes=m) # 開32線程的線程池

result.append(pool.apply_async(generate_flow_field, (file_list[i: i+n],))) # 對每一個list都用上面我們定義的函數(shù)進行處理

f = open('blogCblog.txt', 'w') #首先先創(chuàng)建一個文件對象，打開方式為w
f.writelines('123456') #用readlines()方法寫入文件

f = open('blogCblog.txt', 'w') #首先先創(chuàng)建一個文件對象，打開方式為w
f.writelines(123456) #用readlines()方法寫入文件