1、pytorch之transforms(numpy数据类型转化为tensor,归一化、resize)

from torchvision import transforms
tensor = transforms.Tensor() #初始化对象
#img_or_np为“PIL Image”或者"numpy.",即你要转化的对象
data = tensor(img_or_np) 
trans_resize = transforms.Resize(512,512)
data = trans_resize(data)
#下面将数据data归一化，计算方法为：image=(image-mean)/std
'''
其中mean和std分别通过(0.5,0.5,0.5)和(0.5,0.5,0.5)进行指定。
原来的0-1最小值0则变成(0-0.5)/0.5=-1，而最大值1则变成(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)