Spatial Augmented Tensor

class aloscene.tensors.spatial_augmented_tensor.SpatialAugmentedTensor(x, *args, cam_intrinsic: Optional[aloscene.camera_calib.CameraIntrinsic] = None, cam_extrinsic: Optional[aloscene.camera_calib.CameraExtrinsic] = None, mask=None, **kwargs)

Bases: aloscene.tensors.augmented_tensor.AugmentedTensor

property H

property HW

property W

append_cam_extrinsic(cam_extrinsic)

append_cam_intrinsic(cam_intrinsic)

append_mask(mask, name=None)

Attach a mask to the frame.

Parameters

mask: aloscene.Mask

Mask to attached to the Frame

name: str

If none, the mask will be attached without name (if possible). Otherwise if no other unnamed mask are attached to the frame, the mask will be added to the set of mask.

batch()

Add a batch dimension on the tensor

Returns

batch_frame: aloscene.Frame

A frame with a batch dimension

static batch_list(sa_tensors, pad_boxes=False)

Given a list of Spatial Augmeted tensor of potentially different size (otherwise cat is enough) this method will create a new set of frame of same size (the max size across the frames) and add to each frame a mask with 1. on the padded area.

Note that in order to work proprly, all attached label must implement the pad method.

Parameters

sa_tensors: list or dict

List of any aloscene.tensors.SpatialAugmentedTensor. If dict is given, this method will be applied on each list of spatial augmented tensors within the list

pad_boxes: bool

By default, do not rescale the boxes attached to the sptial augmented Tensor (see explanation in boxes2d.pad)

Returns

aloscene.tensors.SpatialAugmentedTensor

A child of aloscene.tensors.SpatialAugmentedTensor (or dict of SpatialAugmentedTensor) with mask label to keep track of the padded areas.

get_view(views=[], exclude=[], size=None, grid_size=None, **kwargs)

Render the spatial augmented tensor.

Parameters

views: list

List of View or AugmentedTensor. If this is AugmentedTensor, the get_view method will be call with default parameters.

excludelist

List of ‘ AugmentedTensor label to exclude from the final view.

sizeint

Size of each element of the grid

Returns

view: View

relative_to_absolute(x, dim, assert_integer=False)

temporal()

Add a temporal dimension on the tensor

Returns

temporal_frame: aloscene.Frame

A frame with a temporal dimension