一.数据的目录格式如下:
用数据的目录作为数据的标签,每个目录下是相应的图片
编写MyData类,重写getitem,init, len方法
from torch.utils.data import Dataset, DataLoader
from PIL import Image
import os
class MyData(Dataset):
def __init__(self, root_dir, label_dir):
self.root_dir = root_dir
self.label_dir = label_dir
self.path = os.path.join(self.root_dir, self.label_dir)
self.image_list = os.listdir(self.path)
def __getitem__(self, idx):
img_name = self.image_list[idx]
img_item_path = os.path.join(self.root_dir, self.label_dir, img_name)
img = Image.open(img_item_path)
label=self.label_dir
return img,label
def __len__(self):
return len(self.image_list)
创建ants_dataset
root_dir = "data/train"
ants_label_dir="ants"
ants_dataset=MyData(root_dir,ants_label_dir)
ants_dataset[0]
(<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=768x512 at 0x2899A830E48>, ‘ants’)
img,label=ants_dataset[0]
img.show()
创建蜜蜂dataset,还可以把两个dataset合并
bees_dataset=MyData(root_dir,bees_label_dir)
len(ants_dataset)
len(bees_dataset)
train_dataset=ants_dataset+bees_dataset
len(train_dataset)
124
121
245