fastdev.utils.struct

Reference: https://github.com/facebookresearch/pytorch3d/blob/89b851e64c7af3a13766462280597a9d06bf9ae7/pytorch3d/structures/utils.py

Module Contents

fastdev.utils.struct.list_to_padded(x: List[torch.Tensor] | Tuple[torch.Tensor], pad_size: Sequence[int] | None = None, pad_value: float | int = 0.0, equisized: bool = False) → torch.Tensor[source]

Transforms a list of N tensors each of shape (Si_0, Si_1, … Si_D) into: - a single tensor of shape (N, pad_size(0), pad_size(1), …, pad_size(D))

if pad_size is provided

  • or a tensor of shape (N, max(Si_0), max(Si_1), …, max(Si_D)) if pad_size is None.

Parameters:

  • x (Union[List[torch.Tensor], Tuple[torch.Tensor]]) – list of Tensors

  • pad_size (Union[Sequence[int], None]) – list(int) specifying the size of the padded tensor. If None (default), the largest size of each dimension is set as the pad_size.

  • pad_value (Union[float, int]) – float value to be used to fill the padded tensor

  • equisized (bool) – bool indicating whether the items in x are of equal size (sometimes this is known and if provided saves computation)

Returns:

tensor consisting of padded input tensors stored

over the newly allocated memory.

Return type:

x_padded

fastdev.utils.struct.padded_to_list(x: torch.Tensor, split_size: Sequence[int] | None = None, dim: int = 0) → List[torch.Tensor][source]

Transforms a padded tensor of shape (N, S_1, S_2, …, S_D) into a list of N tensors of shape: - (Si_1, Si_2, …, Si_D) where (Si_1, Si_2, …, Si_D) is specified in split_size(i) - or (S_1, S_2, …, S_D) if split_size is None - or (Si_1, S_2, …, S_D) if split_size(i) is an integer.

Parameters:

  • x (torch.Tensor) – tensor

  • split_size (Union[Sequence[int], None]) – optional 1D list/tuple of ints defining the number of items for each tensor.

  • dim (int)

Returns:

a list of tensors sharing the memory with the input.

Return type:

x_list

fastdev.utils.struct.list_to_packed(x: List[torch.Tensor]) → Tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor][source]

Transforms a list of N tensors each of shape (Mi, K, …) into a single tensor of shape (sum(Mi), K, …).

Parameters:

x (List[torch.Tensor]) – list of tensors.

Returns:

4-element tuple containing

  • x_packed: tensor consisting of packed input tensors along the 1st dimension.

  • num_items: tensor of shape N containing Mi for each element in x.

  • item_packed_first_idx: tensor of shape N indicating the index of the first item belonging to the same element in the original list.

  • item_packed_to_list_idx: tensor of shape sum(Mi) containing the index of the element in the list the item belongs to.

Return type:

Tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]

fastdev.utils.struct.packed_to_list(x: torch.Tensor, split_size: Sequence[int] | int) → List[torch.Tensor][source]

Transforms a tensor of shape (sum(Mi), K, L, …) to N set of tensors of shape (Mi, K, L, …) where Mi’s are defined in split_size

Parameters:

  • x (torch.Tensor) – tensor

  • split_size (Union[Sequence[int], int]) – list, tuple or int defining the number of items for each tensor in the output list.

Returns:

A list of Tensors

Return type:

x_list

fastdev.utils.struct.list_to_padded_numpy(x: List[numpy.ndarray], pad_size: Sequence[int] | None = None, pad_value: float | int = 0.0, equisized: bool = False) → numpy.ndarray[source]

Transforms a list of N numpy arrays each of shape (Si_0, Si_1, … Si_D) into: - a single array of shape (N, pad_size(0), pad_size(1), …, pad_size(D))

if pad_size is provided

  • or an array of shape (N, max(Si_0), max(Si_1), …, max(Si_D)) if pad_size is None.

Parameters:

  • x (List[numpy.ndarray]) – list of numpy arrays

  • pad_size (Union[Sequence[int], None]) – list(int) specifying the size of the padded array. If None (default), the largest size of each dimension is set as the pad_size.

  • pad_value (Union[float, int]) – float/int value to be used to fill the padded array

  • equisized (bool) – bool indicating whether the items in x are of equal size

Returns:

numpy array consisting of padded input arrays

Return type:

x_padded

fastdev.utils.struct.list_to_packed_numpy(x: List[numpy.ndarray]) → Tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray, numpy.ndarray][source]

Transforms a list of N numpy arrays each of shape (Mi, K, …) into a single array of shape (sum(Mi), K, …).

Parameters:

x (List[numpy.ndarray]) – list of numpy arrays.

Returns:

4-element tuple containing

  • x_packed: array consisting of packed input arrays along the 1st dimension.

  • num_items: array of shape N containing Mi for each element in x.

  • item_packed_first_idx: array of shape N indicating the index of the first item belonging to the same element in the original list.

  • item_packed_to_list_idx: array of shape sum(Mi) containing the index of the element in the list the item belongs to.

Return type:

Tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray, numpy.ndarray]