Pytorch's transforms (numpy data type is converted to tensor, normalized and resized)

pytorch transform Common formats

from torchvision import transforms
tensor = transforms.Tensor() # Initialize object 
#img_or_np by “PIL Image” perhaps "numpy.", That is, the object you want to transform 
data = tensor(img_or_np) 
trans_resize = transforms.Resize(512,512)
data = trans_resize(data)
# Next, the data data normalization , The calculation method is as follows ：image=(image-mean)/std
'''  among mean and std Pass respectively (0.5,0.5,0.5) and (0.5,0.5,0.5) Make a designation .  The original 0-1 minimum value 0 Has become a (0-0.5)/0.5=-1, And the maximum 1 Has become a (1-0.5)/0.5=1. '''
trans_norm = transforms.Normalize([0.5,0.5,0.5],[0.5,0.5,0.5])
img_normal = trans_norm(data)