1、手上目前拥有数据集是一大坨，没有train，test，val的划分
如图所示
2、目录结构：
|
1
2
3
4
5
6
7
|
|---data
|---dslr
|---images
|---back_pack
|---a.jpg
|---b.jpg
...
|
3、转换后的格式如图
目录结构为：
|
1
2
3
4
5
6
7
8
9
10
|
|---datanews
|---dslr
|---images
|---test
|---train
|---valid
|---back_pack
|---a.jpg
|---b.jpg
...
|
4、代码如下：
4.1 先创建同样结构的层级结构
4.2 然后讲原始数据按照比例划分
4.3 移入到对应的文件目录里面
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
|
import os, random, shutil
def make_dir(source, target):
'''
创建和源文件相似的文件路径函数
:param source: 源文件位置
:param target: 目标文件位置
'''
dir_names = os.listdir(source)
for names in dir_names:
for i in ['train', 'valid', 'test']:
path = target + '/' + i + '/' + names
if not os.path.exists(path):
os.makedirs(path)
def divideTrainValiTest(source, target):
'''
创建和源文件相似的文件路径
:param source: 源文件位置
:param target: 目标文件位置
'''
# 得到源文件下的种类
pic_name = os.listdir(source)
# 对于每一类里的数据进行操作
for classes in pic_name:
# 得到这一种类的图片的名字
pic_classes_name = os.listdir(os.path.join(source, classes))
random.shuffle(pic_classes_name)
# 按照8：1：1比例划分
train_list = pic_classes_name[0:int(0.8 * len(pic_classes_name))]
valid_list = pic_classes_name[int(0.8 * len(pic_classes_name)):int(0.9 * len(pic_classes_name))]
test_list = pic_classes_name[int(0.9 * len(pic_classes_name)):]
# 对于每个图片，移入到对应的文件夹里面
for train_pic in train_list:
shutil.copyfile(source + '/' + classes + '/' + train_pic, target + '/train/' + classes + '/' + train_pic)
for validation_pic in valid_list:
shutil.copyfile(source + '/' + classes + '/' + validation_pic,
target + '/valid/' + classes + '/' + validation_pic)
for test_pic in test_list:
shutil.copyfile(source + '/' + classes + '/' + test_pic, target + '/test/' + classes + '/' + test_pic)
if __name__ == '__main__':
filepath = r'../data/dslr/images'
dist = r'../datanews/dslr/images'
make_dir(filepath, dist)
divideTrainValiTest(filepath, dist)
|
补充：pytorch中数据集的划分方法及eError: take(): argument 'index' (position 1) must be Tensor, not numpy.ndarray错误原因
在使用pytorch框架时，难免需要对数据集进行训练集和验证集的划分，一般使用sklearn.model_selection中的train_test_split方法
该方法使用如下：
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
|
from sklearn.model_selection import train_test_split
import numpy as np
import torch
import torch.autograd import Variable
from torch.utils.data import DataLoader
traindata = np.load(train_path) # image_num * W * H
trainlabel = np.load(train_label_path)
train_data = traindata[:, np.newaxis, ...]
train_label_data = trainlabel[:, np.newaxis, ...]
x_tra, x_val, y_tra, y_val = train_test_split(train_data, train_label_data, test_size=0.1, random_state=0) # 训练集和验证集使用9:1
x_tra = Variable(torch.from_numpy(x_tra))
x_tra = x_tra.float()
y_tra = Variable(torch.from_numpy(y_tra))
y_tra = y_tra.float()
x_val = Variable(torch.from_numpy(x_val))
x_val = x_val.float()
y_val = Variable(torch.from_numpy(y_val))
y_val = y_val.float()
# 训练集的DataLoader
traindataset = torch.utils.data.TensorDataset(x_tra, y_tra)
trainloader = DataLoader(dataset=traindataset, num_workers=opt.threads, batch_size=8, shuffle=True)
# 验证集的DataLoader
validataset = torch.utils.data.TensorDataset(x_val, y_val)
valiloader = DataLoader(dataset=validataset, num_workers=opt.threads, batch_size=opt.batchSize, shuffle=True)
|
注意：如果按照如下方式使用，就会报eError: take(): argument 'index' (position 1) must be Tensor, not numpy.ndarray错误
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
|
from sklearn.model_selection import train_test_split
import numpy as np
import torch
import torch.autograd import Variable
from torch.utils.data import DataLoader
traindata = np.load(train_path) # image_num * W * H
trainlabel = np.load(train_label_path)
train_data = traindata[:, np.newaxis, ...]
train_label_data = trainlabel[:, np.newaxis, ...]
x_train = Variable(torch.from_numpy(train_data))
x_train = x_train.float()
y_train = Variable(torch.from_numpy(train_label_data))
y_train = y_train.float()
# 将原始的训练数据集分为训练集和验证集，后面就可以使用早停机制
x_tra, x_val, y_tra, y_val = train_test_split(x_train, y_train, test_size=0.1) # 训练集和验证集使用9:1
|
报错原因：
train_test_split方法接受的x_train,y_train格式应该为numpy.ndarray 而不应该是Tensor，这点需要注意。
以上为个人经验，希望能给大家一个参考，也希望大家多多支持服务器之家。
原文链接：https://blog.csdn.net/l8947943/article/details/105696192