如需轉(zhuǎn)載，請注明：來源于 深度學(xué)習(xí)—自有圖像數(shù)據(jù)集劃分 | 老五筆記? ? ?

要對自有圖像數(shù)據(jù)集進(jìn)行圖像分類，首選需要將自有圖像數(shù)據(jù)集劃分為train和val(或者test）數(shù)據(jù)集。

? ? ? ?當(dāng)然?前提是將自有圖像數(shù)據(jù)集已經(jīng)按照分類進(jìn)行了預(yù)處理，每個分類的圖像作為一個單獨的目錄。然后劃分train和val的代碼如下所示：

import os
import random
import shutil
from shutil import copy2

def data_set_split(src_data_folder, target_data_folder, train_scale=0.8, val_scale=0.1, test_scale=0.1):
        #讀取源數(shù)據(jù)文件夾，生成劃分好的文件夾，分為trian、val、test三個文件夾
    print("開始數(shù)據(jù)集劃分")
    class_names = os.listdir(src_data_folder)
    split_names = ['train', 'val', 'test']
    for split_name in split_names:
        split_path = os.path.join(target_data_folder, split_name)
        if os.path.isdir(split_path):
            pass
        else:
            os.mkdir(split_path)
        for class_name in class_names:
            class_split_path = os.path.join(split_path, class_name)
            if os.path.isdir(class_split_path):
                pass
            else:
                os.mkdir(class_split_path)

    for class_name in class_names:
        current_class_data_path = os.path.join(src_data_folder, class_name)
        current_all_data = os.listdir(current_class_data_path)
        current_data_length = len(current_all_data)
        current_data_index_list = list(range(current_data_length))
        random.shuffle(current_data_index_list)

        train_folder = os.path.join(os.path.join(target_data_folder, 'train'), class_name)
        val_folder = os.path.join(os.path.join(target_data_folder, 'val'), class_name)
        test_folder = os.path.join(os.path.join(target_data_folder, 'test'), class_name)
        train_stop_flag = current_data_length * train_scale
        val_stop_flag = current_data_length * (train_scale + val_scale)
        current_idx = 0
        train_num = 0
        val_num = 0
        test_num = 0
        for i in current_data_index_list:
            src_img_path = os.path.join(current_class_data_path, current_all_data[i])
            if current_idx <= train_stop_flag:
                copy2(src_img_path, train_folder)
                train_num = train_num + 1
            elif (current_idx > train_stop_flag) and (current_idx <= val_stop_flag):
                copy2(src_img_path, val_folder)
                val_num = val_num + 1
            else:
                copy2(src_img_path, test_folder)
                test_num = test_num + 1

            current_idx = current_idx + 1

        print("*********************************{}*************************************".format(class_name))
        print("{}類按照{(diào)}：{}：{}的比例劃分完成，一共{}張圖片".format(class_name, train_scale, val_scale, test_scale, current_data_length))
        print("訓(xùn)練集{}：{}張".format(train_folder, train_num))
        print("驗證集{}：{}張".format(val_folder, val_num))
        print("測試集{}：{}張".format(test_folder, test_num))


src_data_folder = "./origin"
target_data_folder = "./demo"
data_set_split(src_data_folder, target_data_folder)

在執(zhí)行了上述代碼之后，實現(xiàn)了自有圖像數(shù)據(jù)集的劃分，然后就可以利用該數(shù)據(jù)集進(jìn)行模型訓(xùn)練了。文章來源地址http://www.zghlxwxcb.cn/news/detail-646471.html

到了這里，關(guān)于深度學(xué)習(xí)---自有圖像數(shù)據(jù)集劃分的文章就介紹完了。如果您還想了解更多內(nèi)容，請在右上角搜索TOY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！