智能數字圖像處理之FastRCNN（pytorch）代碼解讀之spilt_data.py

這是一個腳本生成train.txt等txt檔案

1.files_path = "./VOCdevkit/VOC2012/Annotations"-》記住檔案路徑

2.if not os.path.exists(files_path):

    print("檔案夾不存在")

    exit(1)-》檢測路徑存不存在

3.val_rate = 0.5-》驗證集比例

4.files_name = sorted([file.split(".")[0] for file in os.listdir(files_path)])-》拼寫并排序并周遊檔案路徑

5.files_num = len(files_name)-》擷取檔案長度

6.val_index = random.sample(range(0, files_num), k=int(files_num*val_rate))-》随機采樣一部分樣本，range(0, files_num)為采樣範圍，k=int(files_num*val_rate)為采樣個數

7.for index, file_name in enumerate(files_name):

    if index in val_index:

        val_files.append(file_name)

    else:

        train_files.append(file_name)-》分割驗證集和訓練集

8.try:

    train_f = open("train.txt", "x")

    eval_f = open("val.txt", "x")

    train_f.write("\n".join(train_files))

    eval_f.write("\n".join(val_files))-》建立txt檔案并放入訓練集和驗證集

except FileExistsError as e:

    print(e)

    exit(1)

import os
import random


files_path = "./VOCdevkit/VOC2012/Annotations"
if not os.path.exists(files_path):
    print("檔案夾不存在")
    exit(1)
val_rate = 0.5

files_name = sorted([file.split(".")[0] for file in os.listdir(files_path)])
files_num = len(files_name)
val_index = random.sample(range(0, files_num), k=int(files_num*val_rate))
train_files = []
val_files = []
for index, file_name in enumerate(files_name):
    if index in val_index:
        val_files.append(file_name)
    else:
        train_files.append(file_name)

try:
    train_f = open("train.txt", "x")
    eval_f = open("val.txt", "x")
    train_f.write("\n".join(train_files))
    eval_f.write("\n".join(val_files))
except FileExistsError as e:
    print(e)
    exit(1)



           

https://github.com/WZMIAOMIAO/deep-learning-for-image-processing