我对Pytorch很陌生。我想知道如何转换大小torch.Size([1, 3, 224, 224])
的张量以在Jupyter笔记本上以图像格式显示。 PIL格式或CV2格式应该可以。
我尝试使用transforms.ToPILImage(x)
,但结果却是这样的格式:ToPILImage(mode=ToPILImage(mode=tensor([[[[1.3034e-16, 1.3034e-16, 1.3034e-16, ..., 1.4475e-16,.
也许我做错了:no_mouth:
答案 0 :(得分:0)
由于图像已被规范化,因此需要对其进行规范化。您必须执行归一化期间执行的相反操作。一种方法是
class UnNormalize(object):
def __init__(self, mean, std):
self.mean = mean
self.std = std
def __call__(self, tensor):
"""
Args:
tensor (Tensor): Tensor image of size (C, H, W) to be normalized.
Returns:
Tensor: Normalized image.
"""
for t, m, s in zip(tensor, self.mean, self.std):
t.mul_(s).add_(m)
# The normalize code -> t.sub_(m).div_(s)
return tensor
要使用此功能,您需要均值和标准差(用于对图像进行标准化)。然后,
unorm = UnNormalize(mean = [0.35675976, 0.37380189, 0.3764753], std = [0.32064945, 0.32098866, 0.32325324])
image = unorm(normalized_image)