transform中的totensor以及normlize的使用

class ToTensor:
    """Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor. This transform does not             
    support torchscript.

对于ToTensor的使用测试， 

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

writer = SummaryWriter("logs")
img = Image.open("C:/Users/Mxx/PycharmProjects/pythonProject4/images_set/GOGOGOGO.png")
print(img)

trans_totensor = transforms.ToTensor() #首先创建一个对象，来使用ToTensor的方法
img_tensor = trans_totensor(img)
writer.add_image("ToTensor",img_tensor)
writer.close()

writer.add_image需要接收一个img_tensor的数据类型

    def add_image(self, tag, img_tensor, global_step=None, walltime=None,     
               dataformats='CHW'):
        """Add image data to summary.

使用tensorboard来查看，转成没。 

 tensorboard --logdir=temp/logs


TensorFlow installation not found - running with reduced feature set.
Serving TensorBoard on localhost; to expose to the network, use a proxy or pass --bind_all
TensorBoard 2.8.0 at http://localhost:6006/ (Press CTRL+C to quit)

成功插入这个img的tensor类型。 

对其进行标准化后查看标准化后的图片类型。 

trans_norm_png = transforms.Normalize([0.5,0.5,0.5,0.5],[0.5,0.5,0.5,0.5])
img_norm = trans_norm_png(img_tensor)
writer.add_image("PNG Normalize",img_norm)