- class torchvision.ops.MultiScaleRoIAlign(featmap_names: List[str], output_size: Union[int, Tuple[int], List[int]], sampling_ratio: int, *, canonical_scale: int = 224, canonical_level: int = 4)¶
Multi-scale RoIAlign pooling, which is useful for detection with or without FPN.
It infers the scale of the pooling via the heuristics specified in eq. 1 of the Feature Pyramid Network paper. They keyword-only parameters
canonical_levelcorrespond respectively to
k0=4in eq. 1, and have the following meaning:
canonical_levelis the target level of the pyramid from which to pool a region of interest with
w x h = canonical_scale x canonical_scale.
featmap_names (List[str]) – the names of the feature maps that will be used for the pooling.
sampling_ratio (int) – sampling ratio for ROIAlign
canonical_scale (int, optional) – canonical_scale for LevelMapper
canonical_level (int, optional) – canonical_level for LevelMapper
>>> m = torchvision.ops.MultiScaleRoIAlign(['feat1', 'feat3'], 3, 2) >>> i = OrderedDict() >>> i['feat1'] = torch.rand(1, 5, 64, 64) >>> i['feat2'] = torch.rand(1, 5, 32, 32) # this feature won't be used in the pooling >>> i['feat3'] = torch.rand(1, 5, 16, 16) >>> # create some random bounding boxes >>> boxes = torch.rand(6, 4) * 256; boxes[:, 2:] += boxes[:, :2] >>> # original image size, before computing the feature maps >>> image_sizes = [(512, 512)] >>> output = m(i, [boxes], image_sizes) >>> print(output.shape) >>> torch.Size([6, 5, 3, 3])
- forward(x: Dict[str, Tensor], boxes: List[Tensor], image_shapes: List[Tuple[int, int]]) Tensor ¶
x (OrderedDict[Tensor]) – feature maps for each level. They are assumed to have all the same number of channels, but they can have different sizes.
boxes (List[Tensor[N, 4]]) – boxes to be used to perform the pooling operation, in (x1, y1, x2, y2) format and in the image reference size, not the feature map reference. The coordinate must satisfy
0 <= x1 < x2and
0 <= y1 < y2.
image_shapes (List[Tuple[height, width]]) – the sizes of each image before they have been fed to a CNN to obtain feature maps. This allows us to infer the scale factor for each one of the levels to be pooled.