如需转载,请注明:来源于 深度学习—自有图像数据集划分 | 老五笔记
要对自有图像数据集进行图像分类,首选需要将自有图像数据集划分为train和val(或者test)数据集。
当然 前提是将自有图像数据集已经按照分类进行了预处理,每个分类的图像作为一个单独的目录。然后划分train和val的代码如下所示:
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):
#读取源数据文件夹,生成划分好的文件夹,分为trian、val、test三个文件夹
print("开始数据集划分")
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("{}类按照{}:{}:{}的比例划分完成,一共{}张图片".format(class_name, train_scale, val_scale, test_scale, current_data_length))
print("训练集{}:{}张".format(train_folder, train_num))
print("验证集{}:{}张".format(val_folder, val_num))
print("测试集{}:{}张".format(test_folder, test_num))
src_data_folder = "./origin"
target_data_folder = "./demo"
data_set_split(src_data_folder, target_data_folder)
在执行了上述代码之后,实现了自有图像数据集的划分,然后就可以利用该数据集进行模型训练了。