计算机视觉实践(街景字符编码识别)(二)
2.数据读取与数据增扩
Pytorch的数据读取机制
DataSet
from torch.utils.data.dataset import Dataset
class SVHNDataset(Dataset):
def __init__(self, img_path, img_label, transform=None):
self.img_path = img_path
self.img_label = img_label
if transform is not None:
self.transform = transform
else:
self.transform = None
def __getitem__(self, index):
img = Image.open(self.img_path[index]).convert('RGB')
if self.transform is not None:
img = self.transform(img)
lbl = np.array(self.img_label[index], dtype=np.int)
lbl = list(lbl) + (5 - len(lbl)) * [10]
return img, torch.from_numpy(np.array(lbl[:5]))
//getitem 接受一个索引,返回一个样本
def __len__(self):
return len(self.img_path)
DataLoader
train_loader = torch.utils.data.DataLoader(
SVHNDataset(train_path, train_label,
transforms.Compose([
transforms.Resize((64, 128)),
transforms.RandomCrop((60, 120)),
transforms.ColorJitter(0.3, 0.3, 0.2),
transforms.RandomRotation(10),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])),
batch_size=40, //批大小
shuffle=True, //是否乱序
num_workers=10, //是否多进程读取数据
)
读取数据
train_path = glob.glob('../input/train/*.png')
train_path.sort()
train_json = json.load(open('../input/train.json'))
train_label = [train_json[x]['label'] for x in train_json]
print(len(train_path), len(train_label))
数据增强
import torchvision.transforms as transforms
//Crop
transforms.RandomCrop(size,
padding = None,
pad_if_needed = False,
fill =0,
padding_mode='constant')
//Rotation
RandomRotation(degrees,
resample= Flase,
expand = Flase,
center = None)
//Flip
RandomHorizontalFlip()
RandonVerticalFlip()
//Pad
transform.Pad()
//color
transform.ColorJitter()
Grayscale()
RandomGrayscale()
//仿射变换
RandomAffine()