*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 ToTensor().
- My post explains ToPILImage() about no arguments.
- My post explains OxfordIIITPet().
PILToTensor() can convert a PIL(Pillow library) image([H, W, C]), Image([..., C, H, W]) to a tensor([C, H, W]) and doesn't scale its values to [0.0, 1.0] as shown below:
*Memos:
- The 1st argument is
img(Required-Type:PIL image, Image ortensor/ndarray(int/float/complex/bool)): *Memos:- A tensor can be 0D or more D.
- A ndarray can be 0D or more D.
- Don't use
img=.
-
v2is recommended to use according to V1 or V2? Which one should I use?.
from torchvision.datasets import OxfordIIITPet from torchvision.transforms.v2 import ToImage, PILToTensor import torch import numpy as np PILToTensor() # PILToTensor() PILImage_data = OxfordIIITPet( root="data", transform=None ) Image_data = OxfordIIITPet( root="data", transform=ToImage() ) Tensor_data = OxfordIIITPet( root="data", transform=PILToTensor() ) Tensor_data # Dataset OxfordIIITPet # Number of datapoints: 3680 # Root location: data # StandardTransform # Transform: PILToTensor() Tensor_data[0] # (tensor([[[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) Tensor_data[0][0].size() # torch.Size([3, 500, 394]) Tensor_data[0][0] # tensor([[[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) 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 ptt = PILToTensor() ptt(PILImage_data) # It's still PIL image. # Dataset OxfordIIITPet # Number of datapoints: 3680 # Root location: data ptt(PILImage_data[0]) # (tensor([[[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) ptt(PILImage_data[0][0]) # tensor([[[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) ptt(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=ptt(PILImage_data[0][0])) plt.imshow(X=ptt(Image_data[0][0])) # TypeError: Invalid shape (3, 500, 394) for image data ptt((torch.tensor(3), 0)) # int64 ptt((torch.tensor(3, dtype=torch.int64), 0)) # (tensor(3), 0) ptt(torch.tensor(3)) # tensor(3) ptt((torch.tensor([0, 1, 2, 3]), 0)) # (tensor([0, 1, 2, 3]), 0) ptt(torch.tensor([0, 1, 2, 3])) # tensor([0, 1, 2, 3]) ptt((torch.tensor([[0, 1, 2, 3]]), 0)) # (tensor([[0, 1, 2, 3]]), 0) ptt(torch.tensor([[0, 1, 2, 3]])) # tensor([[0, 1, 2, 3]]) ptt((torch.tensor([[[0, 1, 2, 3]]]), 0)) # (tensor([[[0, 1, 2, 3]]]), 0) ptt(torch.tensor([[[0, 1, 2, 3]]])) # tensor([[[0, 1, 2, 3]]]) ptt((torch.tensor([[[[0, 1, 2, 3]]]]), 0)) # (tensor([[[[0, 1, 2, 3]]]]), 0) ptt(torch.tensor([[[[0, 1, 2, 3]]]])) # tensor([[[[0, 1, 2, 3]]]]) ptt((torch.tensor([[[[[0, 1, 2, 3]]]]]), 0)) # (tensor([[[[[0, 1, 2, 3]]]]]), 0) ptt(torch.tensor([[[[[0, 1, 2, 3]]]]])) # tensor([[[[[0, 1, 2, 3]]]]]) ptt((torch.tensor([[0, 1, 2, 3]], dtype=torch.int32), 0)) # (tensor([[0, 1, 2, 3]], dtype=torch.int32), 0) ptt((torch.tensor([[0, 1, 2, 3]], dtype=torch.uint8), 0)) # (tensor([[0, 1, 2, 3]], dtype=torch.uint8), 0) ptt((torch.tensor([[0., 1., 2., 3.]]), 0)) # float32 ptt((torch.tensor([[0., 1., 2., 3.]], dtype=torch.float32), 0)) # (tensor([[0., 1., 2., 3.]]), 0) ptt((torch.tensor([[0., 1., 2., 3.]], dtype=torch.float64), 0)) # (tensor([[0., 1., 2., 3.]], dtype=torch.float64), 0) ptt((torch.tensor([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]]), 0)) # complex64 ptt((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) ptt((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) ptt((torch.tensor([[True, False, True, False]]), 0)) # bool ptt((torch.tensor([[True, False, True, False]], dtype=torch.bool), 0)) # (tensor([[True, False, True, False]]), 0) ptt((np.array(3), 0)) # int32 ptt((np.array(3, dtype=np.int32), 0)) # (array(3), 0) ptt(np.array(3)) # array(3) ptt((np.array([0, 1, 2, 3], dtype=np.int32), 0)) # (array([0, 1, 2, 3]), 0) ptt(np.array([0, 1, 2, 3], dtype=np.int32)) # array([0, 1, 2, 3]) ptt((np.array([[0, 1, 2, 3]], dtype=np.int32), 0)) # (array([[0, 1, 2, 3]]), 0) ptt(np.array([[0, 1, 2, 3]], dtype=np.int32)) # array([[0, 1, 2, 3]]) ptt((np.array([[[0, 1, 2, 3]]]), 0)) # (array([[[0, 1, 2, 3]]]), 0) ptt(np.array([[[0, 1, 2, 3]]])) # array([[[0, 1, 2, 3]]]) ptt((np.array([[[[0, 1, 2, 3]]]]), 0)) # (array([[[[0, 1, 2, 3]]]]), 0) ptt(np.array([[[[0, 1, 2, 3]]]])) # array([[[[0, 1, 2, 3]]]]) ptt((np.array([[[[[0, 1, 2, 3]]]]]), 0)) # (array([[[[[0, 1, 2, 3]]]]]), 0) ptt(np.array([[[[[0, 1, 2, 3]]]]])) # array([[[[[0, 1, 2, 3]]]]]) ptt((np.array([[0, 1, 2, 3]], dtype=np.int64), 0)) # (array([[0, 1, 2, 3]], dtype=int64), 0) ptt((np.array([[0, 1, 2, 3]], dtype=np.uint8), 0)) # (array([[0, 1, 2, 3]], dtype=uint8), 0) ptt((np.array([[0, 1, 2., 3.]], dtype=np.uint16), 0)) # (array([[0, 1, 2, 3]], dtype=uint16), 0) ptt((np.array([[0., 1., 2., 3.]]), 0)) # float64 ptt((np.array([[0., 1., 2., 3.]], dtype=np.float64), 0)) # (array([[0., 1., 2., 3.]]), 0) ptt((np.array([[0., 1., 2., 3.]], dtype=np.float32), 0)) # (array([[0., 1., 2., 3.]], dtype=float32), 0) ptt((np.array([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]]), 0)) # complex128 ptt((np.array([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]], dtype=np.complex128), 0)) # (array([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]]), 0) ptt((np.array([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]], dtype=np.complex64), 0)) # (array([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]], dtype=complex64), 0) ptt((np.array([[True, False, True, False]]), 0)) # bool ptt((np.array([[True, False, True, False]], dtype=bool), 0)) # (array([[True, False, True, False]]), 0) 
Top comments (0)
Some comments may only be visible to logged-in visitors. Sign in to view all comments. Some comments have been hidden by the post's author - find out more