使用不同框架的时候,数据归一化操作toTensor和Normalize时,发现mean和std取值不同,本质都是imagenet的mean和std,下面阅读相应代码比较不同之处
1. Pytorch
torchvison.transform.toTensor()
class ToTensor:
"""Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor. This transform does not support torchscript.
Converts a PIL Image or numpy.ndarray (H x W x C) in the range
[0, 255] to a torch.FloatTensor of shape (C x H x W) in the range [0.0, 1.0]
if the PIL Image belongs to one of the modes (L, LA, P, I, F, RGB, YCbCr, RGBA, CMYK, 1)
or if the numpy.ndarray has dtype = np.uint8
In the other cases, tensors are returned without scaling.
.. note::
Because the input image is scaled to [0.0, 1.0], this transformation should not be used when
transforming target image masks. See the `references`_ for implementing the transforms for image masks.
.. _references: https://github.com/pytorch/vision/tree/master/references/segmentation
"""
def __call__(self, pic):
"""
Args:
pic (PIL Image or numpy.ndarray): Image to be converted to tensor.
Returns:
Tensor: Converted image.
"""
return F.to_tensor(pic)
def __repr__(self):
return self.__class__.__name__ + '()'
F.to_tensor(pic)中有以下语句,将img矩阵/255,从0-255范围变成0-1范围
img.to(dtype=default_float_dtype).div(255)
torchvison.transform.Normalize()
所以pytorch Normalize的mean和std取:
-
mean = [0.485, 0.456, 0.406]
-
Std = [0.229, 0.224, 0.225]
2. MMDetection
mmdetection的pipelines中有ToTensor和Normalize
但此处的ToTensor没有/255的操作,所以mmdetection中的mean和std取:
-
mean = [123.675, 116.28, 103.53],
-
std = [58.395, 57.12, 57.375]
和 pytorch中的mean、std是*255的关系
3. Detectron2
Detectron2中ToTensor和Normalize和Pytorch类似