Library Call
1
2
3
4
5
6
7
8
import os
import random
import numpy as np
import torch
import torch.nn as nn
import torchvision.datasets as datasets
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
1
2
device = 'cuda' if torch.cuda.is_available() else 'cpu'
device
1
'cuda'
1
2
3
4
5
6
7
8
9
10
11
# seed 고정
def seed_everything(seed):
random.seed(seed)
os.environ['PYTHONHASHSEED'] = str(seed)
np.random.seed(seed)
torch.manual_seed(seed)
torch.cuda.manual_seed(seed)
torch.backends.cudnn.deterministic=True
torch.backends.cudnn.benchmark=False
seed_everything(111)
transforms.Compose()는 transform을 여러 개 수행할 경우 묶어주는 역할transforms.Resize((height, width)): image size 변경ImageFolder를 사용해 이미지 불러옴
1
2
3
trans = transforms.Compose([transforms.Resize((64, 128))])
train_data = torchvision.datasets.ImageFolder(root='', transform=trans)
주의할 점은 data.save에 지정된 path에 폴더가 생성되어 있어야 한다.
1
2
3
4
5
6
7
8
9
for num, value in enumerate(train_data):
# data(image information), label
data, label = value
print(num, data, label)
if (label == 0):
data.save('custom_data/train_data/gray/%d_%d.jpeg'%(num, label))
else:
data.save('custom_data/train_data/red/%d_%d.jpeg'%(num, label))
- 초창기 데이터 학습을 위해 train image data를 불러올 때
1
data_loader = DataLoader(dataset = train_data, batch_size = 8, shuffle = True, num_workers=2)
- 모델 학습 이후 예측을 위해 test image data를 불러올 때
1
test_set = DataLoader(dataset = test_data, batch_size = len(test_data))