vis4d.op.box.poolers

Init sampler module.

class RoIPooler(resolution)

Base class for RoI poolers.

__init__(resolution)

Creates an instance of the class.

abstract forward(features, boxes)

Pool features in input bounding boxes from given feature maps.

Return type:

Tensor

class MultiScaleRoIAlign(sampling_ratio, *args, **kwargs)

RoI Align supporting multi-scale inputs.

__init__(sampling_ratio, *args, **kwargs)

Creates an instance of the class.

class MultiScaleRoIPool(resolution, strides, canonical_box_size=224, canonical_level=4, aligned=True)

RoI Pool supporting multi-scale inputs.

class MultiScaleRoIPooler(resolution, strides, canonical_box_size=224, canonical_level=4, aligned=True)

Wrapper for roi pooling that supports multi-scale feature maps.

__init__(resolution, strides, canonical_box_size=224, canonical_level=4, aligned=True)

Multi-scale version of arbitrary RoI pooling operations.

Parameters:

• resolution (tuple[int, int]) – Pooler resolution.

• strides (list[int]) – Feature map strides relative to the input. The strides must be powers of 2 and a monotically decreasing geometric sequence with a factor of 1/2.

• canonical_box_size (int) – Canonical box size in pixels (sqrt(box area)). The default is heuristically defined as 224 pixels in the FPN paper (based on ImageNet pre-training).

• canonical_level (int) – The feature map level index from which a canonical sized box should be placed. The default is defined as level 4 (stride=16) in the FPN paper, i.e., a box of size 224x224 will be placed on the feature with stride=16. The box placement for all boxes will be determined from their sizes w.r.t canonical_box_size. For example, a box whose area is 4x that of a canonical box should be used to pool features from feature level canonical_level+1.

• aligned (bool) – For roi_align op. Shift the box coordinates it by -0.5 for a better alignment with the two neighboring pixel indices.

forward(features, boxes)

Torchvision based roi pooling operation.

Parameters:

• features (list[Tensor]) – List of image feature tensors (e.g., fpn levels) - NCHW format.

• boxes (list[Tensor]) – List of proposals (per image).

Returns:

NCHW format, where N = num boxes (total),

HW is roi size, C is feature dim. Boxes are concatenated along dimension 0 for all batch elements.

Return type:

torch.Tensor

Modules

base	RoI Pooling module base.
roi_pooler	Vis4D RoI Pooling module.
utils	Utility functions for RoI poolers.