DEV Community

Super Kai (Kazuya Ito)
Super Kai (Kazuya Ito)

Posted on • Edited on

ToDtype in PyTorch (1)

#python #pytorch #todtype #v2

Buy Me a Coffee☕

*Memos:

ToDtype() can set a dtype to an Image, Video or tensor and scale its values as shown below. *It's about scale=True:
*Memos:

  • The 1st argument for initialization is dtype(Required-Type:Union[dtype, Dict[Union[Type, str], Optional[dtype]]): *Memos:
    • It converts Image, Video or tensor.
    • A dictionary can do more specific conversions, e.g. dtype={tv_tensors.Image: torch.float32, tv_tensors.Mask: torch.int64, "others":None}.
  • The 2nd argument for initialization is scale(Optional-Default:False-Type:bool): *Memos:
    • If it's True, the values of an Image, Video or tensor is scaled to [0.0, 1.0].
    • Depending of the combinations of the dtypes of ToDtype() and Image, Video or tensor, convertion and scale cannot be done.
  • The 1st argument is img(Required-Type:PIL image or tensor/ndarray(int/float/complex/bool)): *Memos:
    • A tensor must be 0D or more D.
    • A ndarray must be 0D or more D.
    • Don't use img=.
  • ToDtype(dtype, scale=True) is the recommended replacement for ConvertImageDtype(dtype). *ConvertImageDtype() is deprecated.
  • 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, ToDtype import torch import numpy as np td = ToDtype(dtype=torch.float32) td = ToDtype(dtype=torch.float32, scale=False) td # ToDtype(scale=False)  PILImage_data = OxfordIIITPet( root="data", transform=None ) Image_data = OxfordIIITPet( root="data", transform=ToImage() ) PILImage_data[0][0].getdata() # [(37, 20, 12), # (35, 18, 10), # (36, 19, 11), # (36, 19, 11), # (37, 18, 11), # ...]  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,)  td = ToDtype(dtype=torch.float32, scale=True) td(PILImage_data) # It's still PIL image. # Dataset OxfordIIITPet # Number of datapoints: 3680 # Root location: data  td(PILImage_data[0]) # (<PIL.Image.Image image mode=RGB size=394x500>, 0)  list(td(PILImage_data[0][0]).getdata()) # [(37, 20, 12), # (35, 18, 10), # (36, 19, 11), # (36, 19, 11), # (37, 18, 11), # ...]  td(Image_data[0]) # (Image([[[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)  td(Image_data[0][0]) # Image([[[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]]],)  td((torch.tensor(3), 0)) # int64 td((torch.tensor(3, dtype=torch.int64), 0)) # (tensor(3.2526e-19), 0)  td(torch.tensor(3)) # tensor(3.2526e-19)  td((torch.tensor([0, 1, 2, 3]), 0)) # (tensor([0.0000e+00, 1.0842e-19, 2.1684e-19, 3.2526e-19]), 0)  td(torch.tensor([0, 1, 2, 3])) # tensor([0.0000e+00, 1.0842e-19, 2.1684e-19, 3.2526e-19])  td((torch.tensor([[0, 1, 2, 3]]), 0)) # (tensor([[0.0000e+00, 1.0842e-19, 2.1684e-19, 3.2526e-19]]), 0)  td(torch.tensor([[0, 1, 2, 3]])) # tensor([[0.0000e+00, 1.0842e-19, 2.1684e-19, 3.2526e-19]])  td((torch.tensor([[[0, 1, 2, 3]]]), 0)) # (tensor([[[0.0000e+00, 1.0842e-19, 2.1684e-19, 3.2526e-19]]]), 0)  td(torch.tensor([[[0, 1, 2, 3]]])) # tensor([[[0.0000e+00, 1.0842e-19, 2.1684e-19, 3.2526e-19]]])  td((torch.tensor([[[[0, 1, 2, 3]]]]), 0)) # (tensor([[[[0.0000e+00, 1.0842e-19, 2.1684e-19, 3.2526e-19]]]]), 0)  td(torch.tensor([[[[0, 1, 2, 3]]]])) # tensor([[[[0.0000e+00, 1.0842e-19, 2.1684e-19, 3.2526e-19]]]])  td((torch.tensor([[[[[0, 1, 2, 3]]]]]), 0)) # (tensor([[[[[0.0000e+00, 1.0842e-19, 2.1684e-19, 3.2526e-19]]]]]), 0)  td(torch.tensor([[[[[0, 1, 2, 3]]]]])) # tensor([[[[[0.0000e+00, 1.0842e-19, 2.1684e-19, 3.2526e-19]]]]])  td((torch.tensor([[0, 1, 2, 3]], dtype=torch.int32), 0)) # (tensor([[0.0000e+00, 4.6566e-10, 9.3132e-10, 1.3970e-09]]), 0)  td((torch.tensor([[0., 1., 2., 3.]]), 0)) # float32 td((torch.tensor([[0., 1., 2., 3.]], dtype=torch.float32), 0)) td((torch.tensor([[0., 1., 2., 3.]], dtype=torch.float64), 0)) td((torch.tensor([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]]), 0)) # complex64 td((torch.tensor([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]], dtype=torch.complex64), 0)) td((torch.tensor([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]], dtype=torch.complex32), 0)) # (tensor([[0., 1., 2., 3.]]), 0)  td((torch.tensor([[True, False, True, False]]), 0)) # bool td((torch.tensor([[True, False, True, False]], dtype=torch.bool), 0)) # (tensor([[1., 0., 1., 0.]]), 0)  td((np.array(3), 0)) # int32 td((np.array(3, dtype=np.int32), 0)) # (array(3), 0)  td(np.array(3)) # array(3)  td((np.array([0, 1, 2, 3]), 0)) # (array([0, 1, 2, 3]), 0)  td(np.array([0, 1, 2, 3])) # array([0, 1, 2, 3])  td((np.array([[0, 1, 2, 3]]), 0)) # (array([[0, 1, 2, 3]]), 0)  td(np.array([[0, 1, 2, 3]])) # array([[0, 1, 2, 3]])  td((np.array([[[0, 1, 2, 3]]]), 0)) # (array([[[0, 1, 2, 3]]]), 0)  td(np.array([[[0, 1, 2, 3]]])) # array([[[0, 1, 2, 3]]])  td((np.array([[[[0, 1, 2, 3]]]]), 0)) # (array([[[[0, 1, 2, 3]]]]), 0)  td(np.array([[[[0, 1, 2, 3]]]])) # array([[[[0, 1, 2, 3]]]])  td((np.array([[[[[0, 1, 2, 3]]]]]), 0)) # (array([[[[[0, 1, 2, 3]]]]]), 0)  td(np.array([[[[[0, 1, 2, 3]]]]])) # array([[[[[0, 1, 2, 3]]]]])  td((np.array([[0, 1, 2, 3]], dtype=np.int64), 0)) # (array([[0, 1, 2, 3]], dtype=int64), 0)  td((np.array([[0., 1., 2., 3.]]), 0)) # float64 td((np.array([[0., 1., 2., 3.]], dtype=np.float64), 0)) # (array([[0., 1., 2., 3.]]), 0)  td((np.array([[0., 1., 2., 3.]], dtype=np.float32), 0)) # (array([[0., 1., 2., 3.]], dtype=float32), 0)  td((np.array([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]]), 0)) # complex128 td((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)  td((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)  td((np.array([[True, False, True, False]]), 0)) # bool td((np.array([[True, False, True, False]], dtype=bool), 0)) # (array([[True, False, True, False]]), 0)  td = ToDtype(dtype=torch.complex64, scale=True) td(PILImage_data) # It's still PIL image. # Dataset OxfordIIITPet # Number of datapoints: 3680 # Root location: data  td(PILImage_data[0]) # (<PIL.Image.Image image mode=RGB size=394x500>, 0)  list(td(PILImage_data[0][0]).getdata()) # [(37, 20, 12), # (35, 18, 10), # (36, 19, 11), # (36, 19, 11), # (37, 18, 11), # ...]  td(Image_data[0]) td(Image_data[0][0]) td((torch.tensor(3), 0)) # int64 td((torch.tensor(3, dtype=torch.int64), 0)) td(torch.tensor(3)) td((torch.tensor([0, 1, 2, 3]), 0)) td(torch.tensor([0, 1, 2, 3])) td((torch.tensor([[0, 1, 2, 3]]), 0)) td(torch.tensor([[0, 1, 2, 3]])) td((torch.tensor([[[0, 1, 2, 3]]]), 0)) td(torch.tensor([[[0, 1, 2, 3]]])) td((torch.tensor([[[[0, 1, 2, 3]]]]), 0)) td(torch.tensor([[[[0, 1, 2, 3]]]])) td((torch.tensor([[[[[0, 1, 2, 3]]]]]), 0)) td(torch.tensor([[[[[0, 1, 2, 3]]]]])) td((torch.tensor([[0, 1, 2, 3]], dtype=torch.int32), 0)) # Error  td((torch.tensor([[0., 1., 2., 3.]]), 0)) # float32 td((torch.tensor([[0., 1., 2., 3.]], dtype=torch.float32), 0)) td((torch.tensor([[0., 1., 2., 3.]], dtype=torch.float64), 0)) # (tensor([[0.0000+0.j, 1.9990+0.j, 3.9980+0.j, 5.9970+0.j]]), 0)  td((torch.tensor([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]]), 0)) # complex64 td((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)  td((torch.tensor([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]], dtype=torch.complex32), 0)) td((torch.tensor([[True, False, True, False]]), 0)) # bool td((torch.tensor([[True, False, True, False]], dtype=torch.bool), 0)) # Error  td((np.array(3), 0)) # int32 td((np.array(3, dtype=np.int32), 0)) # (array(3), 0)  td(np.array(3)) # array(3)  td((np.array([0, 1, 2, 3]), 0)) # (array([0, 1, 2, 3]), 0)  td(np.array([0, 1, 2, 3])) # array([0, 1, 2, 3])  td((np.array([[0, 1, 2, 3]]), 0)) # (array([[0, 1, 2, 3]]), 0)  td(np.array([[0, 1, 2, 3]])) # array([[0, 1, 2, 3]])  td((np.array([[[0, 1, 2, 3]]]), 0)) # (array([[[0, 1, 2, 3]]]), 0)  td(np.array([[[0, 1, 2, 3]]])) # array([[[0, 1, 2, 3]]])  td((np.array([[0, 1, 2, 3]], dtype=np.int64), 0)) # (array([[0, 1, 2, 3]], dtype=int64), 0)  td((np.array([[0., 1., 2., 3.]]), 0)) # float64 td((np.array([[0., 1., 2., 3.]], dtype=np.float64), 0)) # (array([[0., 1., 2., 3.]]), 0)  td((np.array([[0., 1., 2., 3.]], dtype=np.float32), 0)) # (array([[0., 1., 2., 3.]], dtype=float32), 0)  td((np.array([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]]), 0)) # complex128 td((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)  td((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)  td((np.array([[True, False, True, False]]), 0)) # bool td((np.array([[True, False, True, False]], dtype=bool), 0)) # (array([[True, False, True, False]]), 0)  td = ToDtype(dtype=torch.bool, scale=True) td(PILImage_data) # It's still PIL image. # Dataset OxfordIIITPet # Number of datapoints: 3680 # Root location: data  td(PILImage_data[0]) # (<PIL.Image.Image image mode=RGB size=394x500>, 0)  list(td(PILImage_data[0][0]).getdata()) # [(37, 20, 12), # (35, 18, 10), # (36, 19, 11), # (36, 19, 11), # (37, 18, 11), # ...]  td(Image_data[0]) td(Image_data[0][0]) td((torch.tensor(3), 0)) # int64 td((torch.tensor(3, dtype=torch.int64), 0)) td(torch.tensor(3)) td((torch.tensor([0, 1, 2, 3]), 0)) td(torch.tensor([0, 1, 2, 3])) td((torch.tensor([[0, 1, 2, 3]]), 0)) td(torch.tensor([[0, 1, 2, 3]])) td((torch.tensor([[[0, 1, 2, 3]]]), 0)) td(torch.tensor([[[0, 1, 2, 3]]])) td((torch.tensor([[[[0, 1, 2, 3]]]]), 0)) td(torch.tensor([[[[0, 1, 2, 3]]]])) td((torch.tensor([[[[[0, 1, 2, 3]]]]]), 0)) td(torch.tensor([[[[[0, 1, 2, 3]]]]])) td((torch.tensor([[0, 1, 2, 3]], dtype=torch.int32), 0)) # Error  td((torch.tensor([[0., 1., 2., 3.]]), 0)) # float32 td((torch.tensor([[0., 1., 2., 3.]], dtype=torch.float32), 0)) td((torch.tensor([[0., 1., 2., 3.]], dtype=torch.float64), 0)) # (tensor([[False, True, True, True]]), 0)  td((torch.tensor([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]]), 0)) # complex64 td((torch.tensor([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]], dtype=torch.complex64), 0)) td((torch.tensor([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]], dtype=torch.complex32), 0)) # Error  td((torch.tensor([[True, False, True, False]]), 0)) # bool td((torch.tensor([[True, False, True, False]], dtype=torch.bool), 0)) # (tensor([[True, False, True, False]]), 0)  td((np.array(3), 0)) # int32 td((np.array(3, dtype=np.int32), 0)) # (array(3), 0)  td(np.array(3)) # array(3)  td((np.array([0, 1, 2, 3]), 0)) # (array([0, 1, 2, 3]), 0)  td(np.array([0, 1, 2, 3])) # array([0, 1, 2, 3])  td((np.array([[0, 1, 2, 3]]), 0)) # (array([[0, 1, 2, 3]]), 0)  td(np.array([[0, 1, 2, 3]])) # array([[0, 1, 2, 3]])  td((np.array([[[0, 1, 2, 3]]]), 0)) # (array([[[0, 1, 2, 3]]]), 0)  td(np.array([[[0, 1, 2, 3]]])) # array([[[0, 1, 2, 3]]])  td((np.array([[0, 1, 2, 3]], dtype=np.int64), 0)) # (array([[0, 1, 2, 3]], dtype=int64), 0)  td((np.array([[0., 1., 2., 3.]]), 0)) # float64 td((np.array([[0., 1., 2., 3.]], dtype=np.float64), 0)) # (array([[0., 1., 2., 3.]]), 0)  td((np.array([[0., 1., 2., 3.]], dtype=np.float32), 0)) # (array([[0., 1., 2., 3.]], dtype=float32), 0)  td((np.array([[0.+0.j, 1.+0.j, 2.+0.j, 3.+0.j]]), 0)) # complex128 td((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)  td((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)  td((np.array([[True, False, True, False]]), 0)) # bool td((np.array([[True, False, True, False]], dtype=bool), 0)) # (array([[True, False, True, False]]), 0)
Enter fullscreen mode Exit fullscreen mode

Top comments (0)