pytorch
Setting the tensors and ndarrays of the 2, 3 and 4 channels of `int64` and `int32` to `ToPILImage()` with `None` for `mode` argument gets errors
🐛 Describe the bug
Setting the tensors and ndarrays of the 2, 3 and 4 channels of int64 and int32 to ToPILImage() with None for mode argument gets the errors as shown below:
from torchvision.transforms.v2 import ToPILImage
import torch
import numpy as np
tp = ToPILImage()
tp = ToPILImage(mode=None)
tp((torch.tensor([[[0]], [[1]]]), 0)) # int64
tp((torch.tensor([[[0]], [[1]], [[2]]]), 0)) #int64
tp((torch.tensor([[[0]], [[1]], [[2]], [[3]]]), 0)) #int64
tp((np.array([[[0, 1]]], dtype=np.int64), 0))
tp((np.array([[[0, 1, 2]]], dtype=np.int64), 0))
tp((np.array([[[0, 1, 2, 3]]], dtype=np.int64), 0))
# Error
tp((torch.tensor([[[0]], [[1]]], dtype=torch.int32), 0))
tp((torch.tensor([[[0]], [[1]], [[2]]], dtype=torch.int32), 0))
tp((torch.tensor([[[0]], [[1]], [[2]], [[3]]], dtype=torch.int32), 0))
tp((np.array([[[0, 1]]]), 0)) #int32
tp((np.array([[[0, 1, 2]]]), 0)) #int32
tp((np.array([[[0, 1, 2, 3]]]), 0)) #int32
# Error
TypeError: Input type int64 is not supported
TypeError: Input type int32 is not supported
But setting the tensors and ndarrays of the 2, 3 and 4 channels of int64 and int32 to ToPILImage() with 'LA', 'RGB', 'YCbCr', 'HSV', 'RGBA', 'CMYK' and 'RGBX' for mode argument works as shown below:
from torchvision.transforms.v2 import ToPILImage
import torch
import numpy as np
tp = ToPILImage(mode="LA")
tp((torch.tensor([[[0]], [[1]]]), 0)) # int64
tp((torch.tensor([[[0]], [[1]]], dtype=torch.int32), 0))
tp((np.array([[[0, 1]]], dtype=np.int64), 0))
tp((np.array([[[0, 1]]]), 0)) #int32
# (<PIL.Image.Image image mode=LA size=1x1>, 0)
tp = ToPILImage(mode="RGB")
tp((torch.tensor([[[0]], [[1]], [[2]]]), 0))
tp((torch.tensor([[[0]], [[1]], [[2]]], dtype=torch.int32), 0))
tp((np.array([[[0, 1, 2]]], dtype=np.int64), 0))
tp((np.array([[[0, 1, 2]]]), 0)) #int32
# (<PIL.Image.Image image mode=RGB size=1x1>, 0)
tp = ToPILImage(mode="YCbCr")
tp((torch.tensor([[[0]], [[1]], [[2]]]), 0))
tp((torch.tensor([[[0]], [[1]], [[2]]], dtype=torch.int32), 0))
tp((np.array([[[0, 1, 2]]], dtype=np.int64), 0))
tp((np.array([[[0, 1, 2]]]), 0)) #int32
# (<PIL.Image.Image image mode=YCbCr size=1x1>, 0)
tp = ToPILImage(mode="HSV")
tp((torch.tensor([[[0]], [[1]], [[2]]]), 0))
tp((torch.tensor([[[0]], [[1]], [[2]]], dtype=torch.int32), 0))
tp((np.array([[[0, 1, 2]]], dtype=np.int64), 0))
tp((np.array([[[0, 1, 2]]]), 0)) #int32
# (<PIL.Image.Image image mode=HSV size=1x1>, 0)
tp = ToPILImage(mode="RGBA")
tp((torch.tensor([[[0]], [[1]], [[2]], [[3]]]), 0))
tp((torch.tensor([[[0]], [[1]], [[2]], [[3]]], dtype=torch.int32), 0))
tp((np.array([[[0, 1, 2, 3]]], dtype=np.int64), 0))
tp((np.array([[[0, 1, 2, 3]]]), 0)) #int32
# (<PIL.Image.Image image mode=RGBA size=1x1>, 0)
tp = ToPILImage(mode="CMYK")
tp((torch.tensor([[[0]], [[1]], [[2]], [[3]]]), 0))
tp((torch.tensor([[[0]], [[1]], [[2]], [[3]]], dtype=torch.int32), 0))
tp((np.array([[[0, 1, 2, 3]]], dtype=np.int64), 0))
tp((np.array([[[0, 1, 2, 3]]]), 0)) #int32
# (<PIL.Image.Image image mode=CMYK size=1x1>, 0)
tp = ToPILImage(mode="RGBX")
tp((torch.tensor([[[0]], [[1]], [[2]], [[3]]]), 0))
tp((torch.tensor([[[0]], [[1]], [[2]], [[3]]], dtype=torch.int32), 0))
tp((np.array([[[0, 1, 2, 3]]], dtype=np.int64), 0))
tp((np.array([[[0, 1, 2, 3]]]), 0)) #int32
# (<PIL.Image.Image image mode=RGBX size=1x1>, 0)
In addition, setting the tensor and ndarray of the 1 channel of int64 to ToPILImage() with None and 'I' for mode argument gets the error as shown below:
from torchvision.transforms.v2 import ToPILImage
import torch
import numpy as np
tp = ToPILImage()
tp = ToPILImage(mode=None)
tp = ToPILImage(mode="I")
tp((torch.tensor([[[0]]]), 0)) # int64
tp((np.array([[[0]]], dtype=np.int64), 0))
# Error
ValueError: Incorrect mode (I) supplied for input type <class 'numpy.dtype'>. Should be None
But setting the tensor and ndarray of the 1 channel of int32 to ToPILImage() with None and 'I' for mode argument works as shown below:
from torchvision.transforms.v2 import ToPILImage
import torch
import numpy as np
tp = ToPILImage()
tp = ToPILImage(mode=None)
tp = ToPILImage(mode="I")
tp((torch.tensor([[[0]]], dtype=torch.int32), 0))
tp((np.array([[[0]]]), 0)) # int32
# (<PIL.Image.Image image mode=I size=1x1>, 0)
Versions
import torchvision
torchvision.__version__ # '0.20.1'
Sorry, I'm struggling to really understand the core of the issue. Are all of the , 0 parameters relevant here? Would appreciate a strictly minimal reproducing error, thanks
