Image conversion#

kornia.image.tensor_to_image(tensor, keepdim=False, force_contiguous=False)[source]#

Convert a PyTorch tensor image to a numpy image.

Convention:

The channels move last, and a single channel is always dropped: \((1, H, W)\) gives \((H, W)\) and \((B, 1, H, W)\) gives \((B, H, W)\). keepdim keeps only the batch axis of a \((1, C, H, W)\) input.
The array shares memory with a CPU tensor whose dtype NumPy supports. A bfloat16 tensor is returned as a float32 copy, a dtype NumPy cannot represent, such as float8_e4m3fn, raises TypeError, a tensor on another device is copied, and force_contiguous=True copies a result that is not contiguous, such as the channels-last view of a contiguous tensor with more than one channel.
The dtype is kept, except bfloat16, which NumPy lacks: it becomes float32.

Parameters:

tensor (Tensor) – image of the form \((H, W)\), \((C, H, W)\) or \((B, C, H, W)\).
keepdim (bool, optional) – If True, keep the batch axis of a \((1, C, H, W)\) input. Default: False
force_contiguous (bool, optional) – If True, call contiguous on the result before converting it to NumPy. Default: False

Return type:

Any

Returns:

image of the form \((H, W)\), \((H, W, C)\), \((B, H, W)\) or \((B, H, W, C)\).

Raises:

Example

>>> img = torch.ones(1, 3, 3)
>>> tensor_to_image(img).shape
(3, 3)

>>> img = torch.ones(3, 4, 4)
>>> tensor_to_image(img).shape
(4, 4, 3)

kornia.image.image_to_tensor(image, keepdim=True)[source]#

Convert a NumPy image to a PyTorch tensor image.

Convention:

The last axis of a 3-D or 4-D array is always the channels: \((H, W, C)\) becomes \((C, H, W)\) and \((B, H, W, C)\) becomes \((B, C, H, W)\). A channels-first \((C, H, W)\) array is not detected: it is read as \((H, W, C)\).
The dtype and the values are kept, so uint8 stays in [0, 255], and the tensor is a view of the array that shares its memory. An array with a negative stride, such as OpenCV’s img[..., ::-1], raises ValueError; pass img[..., ::-1].copy().
keepdim defaults to True here and to False in ImageToTensor.
Files and arrays relates it to torchvision’s ToTensor.

Parameters:

image (Any) – image of the form \((H, W, C)\), \((H, W)\) or \((B, H, W, C)\).
keepdim (bool, optional) – If False, a 2-D or 3-D input gets a leading batch axis, \((1, C, H, W)\). A 4-D input is always \((B, C, H, W)\). Default: True

Return type:

Tensor

Returns:

tensor of the form \((C, H, W)\) for a 2-D or 3-D input with keepdim=True (a 2-D input has \(C = 1\)), and \((B, C, H, W)\) otherwise.

Raises:

Example

>>> img = np.ones((3, 3))
>>> image_to_tensor(img).shape
torch.Size([1, 3, 3])

>>> img = np.ones((4, 4, 1))
>>> image_to_tensor(img).shape
torch.Size([1, 4, 4])

>>> img = np.ones((4, 4, 3))
>>> image_to_tensor(img, keepdim=False).shape
torch.Size([1, 3, 4, 4])

kornia.image.image_list_to_tensor(images)[source]#

Convert a list of numpy images to a PyTorch 4d tensor image.

Convention:: See the Convention block of image_to_tensor(). Unlike it, this function copies the images into a new tensor and takes \((H, W, C)\) images only.

Parameters:: images (List[Any]) – list of images, each of the form \((H, W, C)\), all of the same shape.
Return type:: Tensor
Returns:: tensor of the form \((B, C, H, W)\).

Example

>>> imgs = [np.ones((4, 4, 1)), np.zeros((4, 4, 1))]
>>> image_list_to_tensor(imgs).shape
torch.Size([2, 1, 4, 4])

class kornia.image.ImageToTensor(keepdim=False)[source]#

Convert a NumPy image to a PyTorch tensor image with image_to_tensor().

Convention:: See the Convention block of image_to_tensor(). Unlike it, keepdim defaults to False, so an \((H, W, C)\) array becomes \((1, C, H, W)\).

Parameters:: keepdim (bool, optional) – If False, a 2-D or 3-D input gets a leading batch axis, \((1, C, H, W)\). A 4-D input is always \((B, C, H, W)\). Default: False