使用Pytorch自定义数据集
参考:https://www.bilibili.com/video/BV1hE411t7RN?spm_id_from=333.999.0.0
蚂蚁蜜蜂/练手数据集:链接: https://pan.baidu.com/s/1jZoTmoFzaTLWh4lKBHVbEA 密码: 5suq
Custom_dataset.py
from torch.utils.data import Dataset
from PIL import Image
import os
# 所有数据集都要继承Dataset类
class MyData(Dataset):
def __init__(self, root_dir, label_dir):
# self 指定了一个类当中的全局变量,该变量可以让后面的函数使用
self.root_dir = root_dir
self.label_dir = label_dir
self.path = os.path.join(self.root_dir, self.label_dir)
# 这里的图片路径不是一张图片的路径,是一个路径数组
self.img_path = os.listdir(self.path)
def __getitem__(self, idx):
img_name = self.img_path[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.img_path)
if __name__ == "__main__":
root_dir = "dataset/train"
ants_label_dir = "ants"
bees_label_dir = "bees"
# 创建蚂蚁的数据集
ants_dataset = MyData(root_dir, ants_label_dir)
# 创建蜜蜂的数据集
bees_dataset = MyData(root_dir, bees_label_dir)
# 返回蚂蚁数据集中第0张图片及其label
img1, label1 = ants_dataset[0]
# 返回蜜蜂数据集中第0张图片及其label
img2, label2 = bees_dataset[0]
img1.show()
print(label1)
img2.show()
print(label2)
train_dataset = ants_dataset + bees_dataset
len1 = len(ants_dataset)
len2 = len(bees_dataset)
len3 = len(train_dataset)
print(len1, len2, len3)