1. ToTensor定义
导入：from torchvision import transforms
通过transforms.ToTensor解决两个问题（PIL image/numpy.ndarray 转化为 tensor ）

ToTensor()返回一个ToTensor的对象(创建具体的工具)，传入pic就会返回一个Tensor类型的图片（使用工具）

2. ToTensor使用（结合tensorboard）

from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms

img_path =  'dataset/train/ants/6743948_2b8c096dda.jpg'
img = Image.open(img_path)
tensor_trans = transforms.ToTensor()
tensor_img = tensor_trans(img)
print(tensor_img)

writer = SummaryWriter("logs")
writer.add_image("Tensor_img",tensor_img)
writer.close()