ToTensor in PyTorch

Buy Me a Coffee☕ Memos: My post explains how to convert and scale a PIL Image to an Image in PyTorch. My post explains Compose(). My post explains ToImage(). My post explains ToDtype() about scale=True. My post explains PILToTensor(). My post explains ToPILImage(). My post explains OxfordIIITPet(). ToTensor() can convert a PIL(Pillow library) Image([H, W, C]), Image([..., C, H, W]) or ndarray to a tensor([C, H, W]) and scale the values of a PIL Image or ndarray to [0.0, 1,0] as shown below: Memos: ToTensor() is deprecated so instead use Compose(transforms=[ToImage(), ToDtype(dtype=torch.float32, scale=True)]) according to the doc. A PIL Image is scaled to [0.0, 1.0] if the PIL Image belongs to one of the modes (L, LA, P, I, F, RGB, YCbCr, RGBA, CMYK, 1). A ndarray is scaled to [0.0, 1.0] if the ndarray is uint8 which is [0, 255]. The 1st argument is img(Required-Type:PIL Image, Image or tensor/ndarray(int/float/complex/bool)): *Memos: A tensor can be 0D or more D. A ndarray must be 2D or 3D. Don't use img=. v2 is recommended to use according to V1 or V2? Which one should I use?. from torchvision.datasets import OxfordIIITPet from torchvision.transforms.v2 import ToImage, ToTensor import torch import numpy as np ToTensor() # ToTensor() PILImage_data = OxfordIIITPet( root="data", transform=None ) Image_data = OxfordIIITPet( root="data", transform=ToImage() ) Tensor_data = OxfordIIITPet( root="data", transform=ToTensor() ) Tensor_data # Dataset OxfordIIITPet # Number of datapoints: 3680 # Root location: data # StandardTransform # Transform: ToTensor() Tensor_data[0] # (tensor([[[0.1451, 0.1373, 0.1412, ..., 0.9686, 0.9765, 0.9765], # [0.1373, 0.1373, 0.1451, ..., 0.9647, 0.9725, 0.9765], # ..., # [0.1098, 0.1098, 0.1059, ..., 0.2314, 0.2549, 0.2980]], # [[0.0784, 0.0706, 0.0745, ..., 0.9725, 0.9725, 0.9725], # [0.0706, 0.0706, 0.0784, ..., 0.9686, 0.9686, 0.9725], # ..., # [0.1059, 0.1059, 0.1059, ..., 0.3686, 0.4157, 0.4588]], # [[0.0471, 0.0392, 0.0431, ..., 0.9922, 0.9922, 0.9922], # [0.0392, 0.0392, 0.0471, ..., 0.9843, 0.9882, 0.9922], # ..., # [0.1373, 0.1373, 0.1373, ..., 0.8392, 0.9098, 0.8745]]]), 0) Tensor_data[0][0].size() # torch.Size([3, 500, 394]) Tensor_data[0][0] # tensor([[[0.1451, 0.1373, 0.1412, ..., 0.9686, 0.9765, 0.9765], # [0.1373, 0.1373, 0.1451, ..., 0.9647, 0.9725, 0.9765], # ..., # [0.1098, 0.1098, 0.1059, ..., 0.2314, 0.2549, 0.2980]], # [[0.0784, 0.0706, 0.0745, ..., 0.9725, 0.9725, 0.9725], # [0.0706, 0.0706, 0.0784, ..., 0.9686, 0.9686, 0.9725], # ..., # [0.1059, 0.1059, 0.1059, ..., 0.3686, 0.4157, 0.4588]], # [[0.0471, 0.0392, 0.0431, ..., 0.9922, 0.9922, 0.9922], # [0.0392, 0.0392, 0.0471, ..., 0.9843, 0.9882, 0.9922], # ..., # [0.1373, 0.1373, 0.1373, ..., 0.8392, 0.9098, 0.8745]]]) Tensor_data[0][1] # 0 import matplotlib.pyplot as plt plt.imshow(X=Tensor_data[0][0]) # TypeError: Invalid shape (3, 500, 394) for image data tt = ToTensor() tt(PILImage_data) # It's still PIL Image. # Dataset OxfordIIITPet # Number of datapoints: 3680 # Root location: data tt(PILImage_data[0]) # (tensor([[[0.1451, 0.1373, 0.1412, ..., 0.9686, 0.9765, 0.9765], # [0.1373, 0.1373, 0.1451, ..., 0.9647, 0.9725, 0.9765], # ..., # [0.1098, 0.1098, 0.1059, ..., 0.2314, 0.2549, 0.2980]], # [[0.0784, 0.0706, 0.0745, ..., 0.9725, 0.9725, 0.9725], # [0.0706, 0.0706, 0.0784, ..., 0.9686, 0.9686, 0.9725], # ..., # [0.1059, 0.1059, 0.1059, ..., 0.3686, 0.4157, 0.4588]], # [[0.0471, 0.0392, 0.0431, ..., 0.9922, 0.9922, 0.9922], # [0.0392, 0.0392, 0.0471, ..., 0.9843, 0.9882, 0.9922], # ..., # [0.1373, 0.1373, 0.1373, ..., 0.8392, 0.9098, 0.8745]]]), 0) tt(PILImage_data[0][0]) # tensor([[[0.1451, 0.1373, 0.1412, ..., 0.9686, 0.9765, 0.9765], # [0.1373, 0.1373, 0.1451, ..., 0.9647, 0.9725, 0.9765], # ..., # [0.1098, 0.1098, 0.1059, ..., 0.2314, 0.2549, 0.2980]], # [[0.0784, 0.0706, 0.0745, ..., 0.9725, 0.9725, 0.9725], # [0.0706, 0.0706, 0.0784, ..., 0.9686, 0.9686, 0.9725], # ..., # [0.1059, 0.1059, 0.1059, ..., 0.3686, 0.4157, 0.4588]], # [[0.0471, 0.0392, 0.0431, ..., 0.9922, 0.9922, 0.9922], # [0.0392, 0.0392, 0.0471, ..., 0.9843, 0.9882, 0.9922], # ..., # [0.1373, 0.1373, 0.1373, ..., 0.8392, 0.9098, 0.8745]]]) tt(Image_data) # It's still `ToImage()`. # Dataset OxfordIIITPet # Number of datapoints: 3680 # Root location: data # StandardTransform # Transform: ToImage() tt(Image_data[0]) # (Image([[[37, 35, 36, ..., 247, 249, 249], # [35, 35, 37, ..., 246, 248, 249], # ..., # [28, 2

Apr 27, 2025 - 06:47

*Memos:

My post explains how to convert and scale a PIL Image to an Image in PyTorch.
My post explains Compose().
My post explains ToImage().
My post explains ToDtype() about scale=True.
My post explains PILToTensor().
My post explains ToPILImage().
My post explains OxfordIIITPet().

ToTensor() can convert a PIL(Pillow library) Image([H, W, C]), Image([..., C, H, W]) or ndarray to a tensor([C, H, W]) and scale the values of a PIL Image or ndarray to [0.0, 1,0] as shown below:
*Memos:

ToTensor() is deprecated so instead use Compose(transforms=[ToImage(), ToDtype(dtype=torch.float32, scale=True)]) according to the doc.
A PIL Image is scaled to [0.0, 1.0] if the PIL Image belongs to one of the modes (L, LA, P, I, F, RGB, YCbCr, RGBA, CMYK, 1).
A ndarray is scaled to [0.0, 1.0] if the ndarray is uint8 which is [0, 255].
The 1st argument is img(Required-Type:PIL Image, Image or tensor/ndarray(int/float/complex/bool)): *Memos:
- A tensor can be 0D or more D.
- A ndarray must be 2D or 3D.
- Don't use img=.
v2 is recommended to use according to V1 or V2? Which one should I use?.

from torchvision.datasets import OxfordIIITPet
from torchvision.transforms.v2 import ToImage, ToTensor
import torch
import numpy as np

ToTensor()
# ToTensor()

PILImage_data = OxfordIIITPet(
    root="data",
    transform=None
)

Image_data = OxfordIIITPet(
    root="data",
    transform=ToImage()
)

Tensor_data = OxfordIIITPet(
    root="data",
    transform=ToTensor()
)

Tensor_data
# Dataset OxfordIIITPet
#     Number of datapoints: 3680
#     Root location: data
#     StandardTransform
# Transform: ToTensor()

Tensor_data[0]
# (tensor([[[0.1451, 0.1373, 0.1412, ..., 0.9686, 0.9765, 0.9765],
#           [0.1373, 0.1373, 0.1451, ..., 0.9647, 0.9725, 0.9765],
#           ...,
#           [0.1098, 0.1098, 0.1059, ..., 0.2314, 0.2549, 0.2980]],
#          [[0.0784, 0.0706, 0.0745, ..., 0.9725, 0.9725, 0.9725],
#           [0.0706, 0.0706, 0.0784, ..., 0.9686, 0.9686, 0.9725],
#           ...,
#           [0.1059, 0.1059, 0.1059, ..., 0.3686, 0.4157, 0.4588]],
#          [[0.0471, 0.0392, 0.0431, ..., 0.9922, 0.9922, 0.9922],
#           [0.0392, 0.0392, 0.0471, ..., 0.9843, 0.9882, 0.9922],
#           ...,
#           [0.1373, 0.1373, 0.1373, ..., 0.8392, 0.9098, 0.8745]]]), 0)

Tensor_data[0][0].size()
# torch.Size([3, 500, 394])

Tensor_data[0][0]
# tensor([[[0.1451, 0.1373, 0.1412, ..., 0.9686, 0.9765, 0.9765],
#          [0.1373, 0.1373, 0.1451, ..., 0.9647, 0.9725, 0.9765],
#          ...,
#          [0.1098, 0.1098, 0.1059, ..., 0.2314, 0.2549, 0.2980]],
#         [[0.0784, 0.0706, 0.0745, ..., 0.9725, 0.9725, 0.9725],
#          [0.0706, 0.0706, 0.0784, ..., 0.9686, 0.9686, 0.9725],
#          ...,
#          [0.1059, 0.1059, 0.1059, ..., 0.3686, 0.4157, 0.4588]],
#         [[0.0471, 0.0392, 0.0431, ..., 0.9922, 0.9922, 0.9922],
#          [0.0392, 0.0392, 0.0471, ..., 0.9843, 0.9882, 0.9922],
#          ...,
#          [0.1373, 0.1373, 0.1373, ..., 0.8392, 0.9098, 0.8745]]])

Tensor_data[0][1]
# 0

import matplotlib.pyplot as plt

plt.imshow(X=Tensor_data[0][0])
# TypeError: Invalid shape (3, 500, 394) for image data

tt = ToTensor()

tt(PILImage_data) # It's still PIL Image.
# Dataset OxfordIIITPet
#     Number of datapoints: 3680
#     Root location: data

tt(PILImage_data[0])
# (tensor([[[0.1451, 0.1373, 0.1412, ..., 0.9686, 0.9765, 0.9765],
#           [0.1373, 0.1373, 0.1451, ..., 0.9647, 0.9725, 0.9765],
#           ...,
#           [0.1098, 0.1098, 0.1059, ..., 0.2314, 0.2549, 0.2980]],
#          [[0.0784, 0.0706, 0.0745, ..., 0.9725, 0.9725, 0.9725],
#           [0.0706, 0.0706, 0.0784, ..., 0.9686, 0.9686, 0.9725],
#           ...,
#           [0.1059, 0.1059, 0.1059, ..., 0.3686, 0.4157, 0.4588]],
#          [[0.0471, 0.0392, 0.0431, ..., 0.9922, 0.9922, 0.9922],
#           [0.0392, 0.0392, 0.0471, ..., 0.9843, 0.9882, 0.9922],
#           ...,
#           [0.1373, 0.1373, 0.1373, ..., 0.8392, 0.9098, 0.8745]]]), 0)

tt(PILImage_data[0][0])
# tensor([[[0.1451, 0.1373, 0.1412, ..., 0.9686, 0.9765, 0.9765],
#          [0.1373, 0.1373, 0.1451, ..., 0.9647, 0.9725, 0.9765],
#          ...,
#          [0.1098, 0.1098, 0.1059, ..., 0.2314, 0.2549, 0.2980]],
#         [[0.0784, 0.0706, 0.0745, ..., 0.9725, 0.9725, 0.9725],
#          [0.0706, 0.0706, 0.0784, ..., 0.9686, 0.9686, 0.9725],
#          ...,
#          [0.1059, 0.1059, 0.1059, ..., 0.3686, 0.4157, 0.4588]],
#         [[0.0471, 0.0392, 0.0431, ..., 0.9922, 0.9922, 0.9922],
#          [0.0392, 0.0392, 0.0471, ..., 0.9843, 0.9882, 0.9922],
#          ...,
#          [0.1373, 0.1373, 0.1373, ..., 0.8392, 0.9098, 0.8745]]])

tt(Image_data) # It's still `ToImage()`.
# Dataset OxfordIIITPet
#     Number of datapoints: 3680
#     Root location: data
#     StandardTransform
# Transform: ToImage()

tt(Image_data[0])
# (Image([[[37, 35, 36, ..., 247, 249, 249],
#          [35, 35, 37, ..., 246, 248, 249],
#          ...,
#          [28, 28, 27, ..., 59, 65, 76]], 
#         [[20, 18, 19, ..., 248, 248, 248],
#          [18, 18, 20, ..., 247, 247, 248],
#          ...,
#          [27, 27, 27, ..., 94, 106, 117]], 
#         [[12, 10, 11, ..., 253, 253, 253],
#          [10, 10, 12, ..., 251, 252, 253],
#          ...,
#          [35, 35, 35, ..., 214, 232, 223]]], dtype=torch.uint8,), 0)

tt(Image_data[0][0])
# Image([[[37, 35, 36, ..., 247, 249, 249],
#         [35, 35, 37, ..., 246, 248, 249],
#         ...,
#         [28, 28, 27, ...,  59,  65,  76]],
#        [[20, 18, 19, ..., 248, 248, 248],
#         [18, 18, 20, ..., 247, 247, 248],
#         ...,
#         [27, 27, 27, ...,  94, 106, 117]],
#        [[12, 10, 11, ..., 253, 253, 253],
#         [10, 10, 12, ..., 251, 252, 253],
#         ...,
#         [35, 35, 35, ..., 214, 232, 223]]], dtype=torch.uint8,)

plt.imshow(X=tt(PILImage_data[0][0]))
plt.imshow(X=tt(Image_data[0][0]))
# TypeError: Invalid shape (3, 500, 394) for image data

tt((torch.tensor(3), 0)) # int64
tt((torch.tensor(3, dtype=torch.int64), 0))
# (tensor(3), 0)

tt(torch.tensor(3))
# tensor(3)

tt((torch.tensor([0, 1, 2, 3]), 0))
# (tensor([0, 1, 2, 3]), 0)

tt(torch.tensor([0, 1, 2, 3]))
# tensor([0, 1, 2, 3])

tt((torch.tensor([[0, 1, 2, 3]]), 0))
# (tensor([[0, 1, 2, 3]]), 0)

tt(torch.tensor([[0, 1, 2, 3]]))
# tensor([[0, 1, 2, 3]])

tt((torch.tensor([[[0, 1, 2, 3]]]), 0))
# (tensor([[[0, 1, 2, 3]]]), 0)

tt(torch.tensor([[[0, 1, 2, 3]]]))
# tensor([[[0, 1, 2, 3]]])

tt((torch.tensor([[[[0, 1, 2, 3]]]]), 0))
# (tensor([[[[0, 1, 2, 3]]]]), 0)

tt(torch.tensor([[[[0, 1, 2, 3]]]]))
# tensor([[[[0, 1, 2, 3]]]])

tt((torch.tensor([[[[[0, 1, 2, 3]]]]]), 0))
# (tensor([[[[[0, 1, 2, 3]]]]]), 0)

tt(torch.tensor([[[[[0, 1, 2, 3]]]]]))
# tensor([[[[[0, 1, 2, 3]]]]])

tt((torch.tensor([[0, 1, 2, 3]], dtype=torch.int32), 0))
# (tensor([[0, 1, 2, 3]], dtype=torch.int32), 0)

tt((torch.tensor([[0, 1, 2, 3]], dtype=torch.uint8), 0))
# (tensor([[0, 1, 2, 3]], dtype=torch.uint8), 0)

tt((torch.tensor([[0., 1., 2., 3.]]), 0)) # float32
tt((torch.tensor([[0., 1., 2., 3.]], dtype=torch.float32), 0))
# (tensor([[0., 1., 2., 3.]]), 0)

tt((torch.tensor([[0., 1., 2., 3.]], dtype=torch.float64), 0))
# (tensor([[0., 1., 2., 3.]], dtype=torch.float64), 0)

tt((torch.tensor([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]]), 0)) # complex64
tt((torch.tensor([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]], dtype=torch.complex64), 0))
# (tensor([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]]), 0)

tt((torch.tensor([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]], dtype=torch.complex32), 0))
# (tensor([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]], dtype=torch.complex32), 0)

tt((torch.tensor([[True, False, True, False]]), 0)) # bool
tt((torch.tensor([[True, False, True, False]], dtype=torch.bool), 0))
# (tensor([[True, False, True, False]]), 0)

tt((np.array([[0, 1, 2, 3]]), 0)) # int32
tt((np.array([[0, 1, 2, 3]], dtype=np.int32), 0))
# (tensor([[[0, 1, 2, 3]]], dtype=torch.int32), 0)

tt((np.array([[[0, 1, 2, 3]]]), 0)) # int32
# (tensor([[[0]], [[1]], [[2]], [[3]]], dtype=torch.int32), 0)

tt((np.array([[0, 1, 2, 3]], dtype=np.int64), 0))
# (tensor([[[0, 1, 2, 3]]]), 0)

tt((np.array([[0, 1, 2, 3]], dtype=np.uint8), 0))
# (tensor([[[0.0000, 0.0039, 0.0078, 0.0118]]]), 0)

tt((np.array([[0, 1, 2, 3]], dtype=np.uint16), 0))
# (tensor([[[0, 1, 2, 3]]], dtype=torch.uint16), 0)

tt((np.array([[0., 1., 2., 3.]]), 0)) # float64
tt((np.array([[0., 1., 2., 3.]], dtype=np.float64), 0))
# (tensor([[[0., 1., 2., 3.]]], dtype=torch.float64), 0)

tt((np.array([[0., 1., 2., 3.]], dtype=np.float32), 0))
# (tensor([[[0., 1., 2., 3.]]]), 0)

tt((np.array([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]]), 0)) # complex128
tt((np.array([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]], dtype=np.complex128), 0))
# (tensor([[[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]]], dtype=torch.complex128), 0)

tt((np.array([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]], dtype=np.complex64), 0))
# (tensor([[[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]]]), 0)

tt((np.array([[True, False, True, False]]), 0)) # bool
tt((np.array([[True, False, True, False]], dtype=bool), 0))
# (tensor([[[ True, False,  True, False]]]), 0)