torchvision.ops¶
torchvision.ops
implements operators that are specific for Computer Vision.
Note
All operators have native support for TorchScript.

torchvision.ops.
nms
(boxes: torch.Tensor, scores: torch.Tensor, iou_threshold: float) → torch.Tensor[source]¶ Performs nonmaximum suppression (NMS) on the boxes according to their intersectionoverunion (IoU).
NMS iteratively removes lower scoring boxes which have an IoU greater than iou_threshold with another (higher scoring) box.
If multiple boxes have the exact same score and satisfy the IoU criterion with respect to a reference box, the selected box is not guaranteed to be the same between CPU and GPU. This is similar to the behavior of argsort in PyTorch when repeated values are present.
Parameters:  boxes (Tensor[N, 4])) – boxes to perform NMS on. They
are expected to be in
(x1, y1, x2, y2)
format with0 <= x1 < x2
and0 <= y1 < y2
.  scores (Tensor[N]) – scores for each one of the boxes
 iou_threshold (float) – discards all overlapping boxes with IoU > iou_threshold
Returns:  int64 tensor with the indices
of the elements that have been kept by NMS, sorted in decreasing order of scores
Return type: keep (Tensor)
 boxes (Tensor[N, 4])) – boxes to perform NMS on. They
are expected to be in

torchvision.ops.
batched_nms
(boxes: torch.Tensor, scores: torch.Tensor, idxs: torch.Tensor, iou_threshold: float) → torch.Tensor[source]¶ Performs nonmaximum suppression in a batched fashion.
Each index value correspond to a category, and NMS will not be applied between elements of different categories.
Parameters:  boxes (Tensor[N, 4]) – boxes where NMS will be performed. They
are expected to be in
(x1, y1, x2, y2)
format with0 <= x1 < x2
and0 <= y1 < y2
.  scores (Tensor[N]) – scores for each one of the boxes
 idxs (Tensor[N]) – indices of the categories for each one of the boxes.
 iou_threshold (float) – discards all overlapping boxes with IoU > iou_threshold
Returns:  int64 tensor with the indices of
the elements that have been kept by NMS, sorted in decreasing order of scores
Return type: keep (Tensor)
 boxes (Tensor[N, 4]) – boxes where NMS will be performed. They
are expected to be in

torchvision.ops.
remove_small_boxes
(boxes: torch.Tensor, min_size: float) → torch.Tensor[source]¶ Remove boxes which contains at least one side smaller than min_size.
Parameters:  boxes (Tensor[N, 4]) – boxes in
(x1, y1, x2, y2)
format with0 <= x1 < x2
and0 <= y1 < y2
.  min_size (float) – minimum size
Returns:  indices of the boxes that have both sides
larger than min_size
Return type: keep (Tensor[K])
 boxes (Tensor[N, 4]) – boxes in

torchvision.ops.
clip_boxes_to_image
(boxes: torch.Tensor, size: Tuple[int, int]) → torch.Tensor[source]¶ Clip boxes so that they lie inside an image of size size.
Parameters:  boxes (Tensor[N, 4]) – boxes in
(x1, y1, x2, y2)
format with0 <= x1 < x2
and0 <= y1 < y2
.  size (Tuple[height, width]) – size of the image
Returns: clipped_boxes (Tensor[N, 4])
 boxes (Tensor[N, 4]) – boxes in

torchvision.ops.
box_convert
(boxes: torch.Tensor, in_fmt: str, out_fmt: str) → torch.Tensor[source]¶ Converts boxes from given in_fmt to out_fmt. Supported in_fmt and out_fmt are:
‘xyxy’: boxes are represented via corners, x1, y1 being top left and x2, y2 being bottom right.
‘xywh’ : boxes are represented via corner, width and height, x1, y2 being top left, w, h being width and height.
‘cxcywh’ : boxes are represented via centre, width and height, cx, cy being center of box, w, h being width and height.
Parameters: Returns: Boxes into converted format.
Return type: boxes (Tensor[N, 4])

torchvision.ops.
box_area
(boxes: torch.Tensor) → torch.Tensor[source]¶ Computes the area of a set of bounding boxes, which are specified by its (x1, y1, x2, y2) coordinates.
Parameters: boxes (Tensor[N, 4]) – boxes for which the area will be computed. They are expected to be in (x1, y1, x2, y2) format with 0 <= x1 < x2
and0 <= y1 < y2
.Returns: area for each box Return type: area (Tensor[N])

torchvision.ops.
box_iou
(boxes1: torch.Tensor, boxes2: torch.Tensor) → torch.Tensor[source]¶ Return intersectionoverunion (Jaccard index) of boxes.
Both sets of boxes are expected to be in
(x1, y1, x2, y2)
format with0 <= x1 < x2
and0 <= y1 < y2
.Parameters:  boxes1 (Tensor[N, 4]) –
 boxes2 (Tensor[M, 4]) –
Returns: the NxM matrix containing the pairwise IoU values for every element in boxes1 and boxes2
Return type: iou (Tensor[N, M])

torchvision.ops.
generalized_box_iou
(boxes1: torch.Tensor, boxes2: torch.Tensor) → torch.Tensor[source]¶ Return generalized intersectionoverunion (Jaccard index) of boxes.
Both sets of boxes are expected to be in
(x1, y1, x2, y2)
format with0 <= x1 < x2
and0 <= y1 < y2
.Parameters:  boxes1 (Tensor[N, 4]) –
 boxes2 (Tensor[M, 4]) –
Returns: the NxM matrix containing the pairwise generalized_IoU values for every element in boxes1 and boxes2
Return type: generalized_iou (Tensor[N, M])

torchvision.ops.
roi_align
(input: torch.Tensor, boxes: torch.Tensor, output_size: None, spatial_scale: float = 1.0, sampling_ratio: int = 1, aligned: bool = False) → torch.Tensor[source]¶ Performs Region of Interest (RoI) Align operator described in Mask RCNN
Parameters:  input (Tensor[N, C, H, W]) – input tensor
 boxes (Tensor[K, 5] or List[Tensor[L, 4]]) – the box coordinates in (x1, y1, x2, y2)
format where the regions will be taken from.
The coordinate must satisfy
0 <= x1 < x2
and0 <= y1 < y2
. If a single Tensor is passed, then the first column should contain the batch index. If a list of Tensors is passed, then each Tensor will correspond to the boxes for an element i in a batch  output_size (int or Tuple[int, int]) – the size of the output after the cropping is performed, as (height, width)
 spatial_scale (float) – a scaling factor that maps the input coordinates to the box coordinates. Default: 1.0
 sampling_ratio (int) – number of sampling points in the interpolation grid used to compute the output value of each pooled output bin. If > 0, then exactly sampling_ratio x sampling_ratio grid points are used. If <= 0, then an adaptive number of grid points are used (computed as ceil(roi_width / pooled_w), and likewise for height). Default: 1
 aligned (bool) – If False, use the legacy implementation. If True, pixel shift it by 0.5 for align more perfectly about two neighboring pixel indices. This version in Detectron2
Returns: output (Tensor[K, C, output_size[0], output_size[1]])

torchvision.ops.
ps_roi_align
(input: torch.Tensor, boxes: torch.Tensor, output_size: int, spatial_scale: float = 1.0, sampling_ratio: int = 1) → torch.Tensor[source]¶ Performs PositionSensitive Region of Interest (RoI) Align operator mentioned in LightHead RCNN.
Parameters:  input (Tensor[N, C, H, W]) – input tensor
 boxes (Tensor[K, 5] or List[Tensor[L, 4]]) – the box coordinates in (x1, y1, x2, y2)
format where the regions will be taken from.
The coordinate must satisfy
0 <= x1 < x2
and0 <= y1 < y2
. If a single Tensor is passed, then the first column should contain the batch index. If a list of Tensors is passed, then each Tensor will correspond to the boxes for an element i in a batch  output_size (int or Tuple[int, int]) – the size of the output after the cropping is performed, as (height, width)
 spatial_scale (float) – a scaling factor that maps the input coordinates to the box coordinates. Default: 1.0
 sampling_ratio (int) – number of sampling points in the interpolation grid used to compute the output value of each pooled output bin. If > 0 then exactly sampling_ratio x sampling_ratio grid points are used. If <= 0, then an adaptive number of grid points are used (computed as ceil(roi_width / pooled_w), and likewise for height). Default: 1
Returns: output (Tensor[K, C, output_size[0], output_size[1]])

torchvision.ops.
roi_pool
(input: torch.Tensor, boxes: torch.Tensor, output_size: None, spatial_scale: float = 1.0) → torch.Tensor[source]¶ Performs Region of Interest (RoI) Pool operator described in Fast RCNN
Parameters:  input (Tensor[N, C, H, W]) – input tensor
 boxes (Tensor[K, 5] or List[Tensor[L, 4]]) – the box coordinates in (x1, y1, x2, y2)
format where the regions will be taken from.
The coordinate must satisfy
0 <= x1 < x2
and0 <= y1 < y2
. If a single Tensor is passed, then the first column should contain the batch index. If a list of Tensors is passed, then each Tensor will correspond to the boxes for an element i in a batch  output_size (int or Tuple[int, int]) – the size of the output after the cropping is performed, as (height, width)
 spatial_scale (float) – a scaling factor that maps the input coordinates to the box coordinates. Default: 1.0
Returns: output (Tensor[K, C, output_size[0], output_size[1]])

torchvision.ops.
ps_roi_pool
(input: torch.Tensor, boxes: torch.Tensor, output_size: int, spatial_scale: float = 1.0) → torch.Tensor[source]¶ Performs PositionSensitive Region of Interest (RoI) Pool operator described in RFCN
Parameters:  input (Tensor[N, C, H, W]) – input tensor
 boxes (Tensor[K, 5] or List[Tensor[L, 4]]) – the box coordinates in (x1, y1, x2, y2)
format where the regions will be taken from.
The coordinate must satisfy
0 <= x1 < x2
and0 <= y1 < y2
. If a single Tensor is passed, then the first column should contain the batch index. If a list of Tensors is passed, then each Tensor will correspond to the boxes for an element i in a batch  output_size (int or Tuple[int, int]) – the size of the output after the cropping is performed, as (height, width)
 spatial_scale (float) – a scaling factor that maps the input coordinates to the box coordinates. Default: 1.0
Returns: output (Tensor[K, C, output_size[0], output_size[1]])

torchvision.ops.
deform_conv2d
(input: torch.Tensor, offset: torch.Tensor, weight: torch.Tensor, bias: Union[torch.Tensor, NoneType] = None, stride: Tuple[int, int] = (1, 1), padding: Tuple[int, int] = (0, 0), dilation: Tuple[int, int] = (1, 1), mask: Union[torch.Tensor, NoneType] = None) → torch.Tensor[source]¶ Performs Deformable Convolution v2, described in Deformable ConvNets v2: More Deformable, Better Results if
mask
is notNone
and Performs Deformable Convolution, described in Deformable Convolutional Networks ifmask
isNone
.Parameters:  input (Tensor[batch_size, in_channels, in_height, in_width]) – input tensor
 (Tensor[batch_size, 2 * offset_groups * kernel_height * kernel_width, (offset) – out_height, out_width]): offsets to be applied for each position in the convolution kernel.
 weight (Tensor[out_channels, in_channels // groups, kernel_height, kernel_width]) – convolution weights, split into groups of size (in_channels // groups)
 bias (Tensor[out_channels]) – optional bias of shape (out_channels,). Default: None
 stride (int or Tuple[int, int]) – distance between convolution centers. Default: 1
 padding (int or Tuple[int, int]) – height/width of padding of zeroes around each image. Default: 0
 dilation (int or Tuple[int, int]) – the spacing between kernel elements. Default: 1
 (Tensor[batch_size, offset_groups * kernel_height * kernel_width, (mask) – out_height, out_width]): masks to be applied for each position in the convolution kernel. Default: None
Returns: result of convolution
Return type: output (Tensor[batch_sz, out_channels, out_h, out_w])
 Examples::
>>> input = torch.rand(4, 3, 10, 10) >>> kh, kw = 3, 3 >>> weight = torch.rand(5, 3, kh, kw) >>> # offset and mask should have the same spatial size as the output >>> # of the convolution. In this case, for an input of 10, stride of 1 >>> # and kernel size of 3, without padding, the output size is 8 >>> offset = torch.rand(4, 2 * kh * kw, 8, 8) >>> mask = torch.rand(4, kh * kw, 8, 8) >>> out = deform_conv2d(input, offset, weight, mask=mask) >>> print(out.shape) >>> # returns >>> torch.Size([4, 5, 8, 8])

torchvision.ops.
sigmoid_focal_loss
(inputs: torch.Tensor, targets: torch.Tensor, alpha: float = 0.25, gamma: float = 2, reduction: str = 'none')[source]¶ Original implementation from https://github.com/facebookresearch/fvcore/blob/master/fvcore/nn/focal_loss.py . Loss used in RetinaNet for dense detection: https://arxiv.org/abs/1708.02002.
Parameters:  inputs – A float tensor of arbitrary shape. The predictions for each example.
 targets – A float tensor with the same shape as inputs. Stores the binary classification label for each element in inputs (0 for the negative class and 1 for the positive class).
 alpha – (optional) Weighting factor in range (0,1) to balance positive vs negative examples or 1 for ignore. Default = 0.25
 gamma – Exponent of the modulating factor (1  p_t) to balance easy vs hard examples.
 reduction – ‘none’  ‘mean’  ‘sum’ ‘none’: No reduction will be applied to the output. ‘mean’: The output will be averaged. ‘sum’: The output will be summed.
Returns: Loss tensor with the reduction option applied.

class
torchvision.ops.
RoIAlign
(output_size: None, spatial_scale: float, sampling_ratio: int, aligned: bool = False)[source]¶ See roi_align

class
torchvision.ops.
PSRoIAlign
(output_size: int, spatial_scale: float, sampling_ratio: int)[source]¶ See ps_roi_align

class
torchvision.ops.
DeformConv2d
(in_channels: int, out_channels: int, kernel_size: int, stride: int = 1, padding: int = 0, dilation: int = 1, groups: int = 1, bias: bool = True)[source]¶ See deform_conv2d

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)[source]¶ Multiscale 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 keywordonly parameters
canonical_scale
andcanonical_level
correspond respectively to224
andk0=4
in eq. 1, and have the following meaning:canonical_level
is the target level of the pyramid from which to pool a region of interest withw x h = canonical_scale x canonical_scale
.Parameters:  featmap_names (List[str]) – the names of the feature maps that will be used for the pooling.
 output_size (List[Tuple[int, int]] or List[int]) – output size for the pooled region
 sampling_ratio (int) – sampling ratio for ROIAlign
 canonical_scale (int, optional) – canonical_scale for LevelMapper
 canonical_level (int, optional) – canonical_level for LevelMapper
Examples:
>>> 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])

class
torchvision.ops.
FeaturePyramidNetwork
(in_channels_list: List[int], out_channels: int, extra_blocks: Union[torchvision.ops.feature_pyramid_network.ExtraFPNBlock, NoneType] = None)[source]¶ Module that adds a FPN from on top of a set of feature maps. This is based on “Feature Pyramid Network for Object Detection”.
The feature maps are currently supposed to be in increasing depth order.
The input to the model is expected to be an OrderedDict[Tensor], containing the feature maps on top of which the FPN will be added.
Parameters:  in_channels_list (list[int]) – number of channels for each feature map that is passed to the module
 out_channels (int) – number of channels of the FPN representation
 extra_blocks (ExtraFPNBlock or None) – if provided, extra operations will be performed. It is expected to take the fpn features, the original features and the names of the original features as input, and returns a new list of feature maps and their corresponding names
Examples:
>>> m = torchvision.ops.FeaturePyramidNetwork([10, 20, 30], 5) >>> # get some dummy data >>> x = OrderedDict() >>> x['feat0'] = torch.rand(1, 10, 64, 64) >>> x['feat2'] = torch.rand(1, 20, 16, 16) >>> x['feat3'] = torch.rand(1, 30, 8, 8) >>> # compute the FPN on top of x >>> output = m(x) >>> print([(k, v.shape) for k, v in output.items()]) >>> # returns >>> [('feat0', torch.Size([1, 5, 64, 64])), >>> ('feat2', torch.Size([1, 5, 16, 16])), >>> ('feat3', torch.Size([1, 5, 8, 8]))]