# torchvision.ops¶

torchvision.ops implements operators that are specific for Computer Vision.

Note

All operators have native support for TorchScript.

torchvision.ops.nms(boxes, scores, iou_threshold)[source]

Performs non-maximum suppression (NMS) on the boxes according to their intersection-over-union (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

• scores (Tensor[N]) – scores for each one of the boxes

• iou_threshold (float) – discards all overlapping boxes with IoU > iou_threshold

Returns

keep – int64 tensor with the indices of the elements that have been kept by NMS, sorted in decreasing order of scores

Return type

Tensor

torchvision.ops.roi_align(input, boxes, output_size, spatial_scale=1.0, sampling_ratio=-1, aligned=False)[source]

Performs Region of Interest (RoI) Align operator described in Mask R-CNN

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. 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, boxes, output_size, spatial_scale=1.0, sampling_ratio=-1)[source]

Performs Position-Sensitive Region of Interest (RoI) Align operator mentioned in Light-Head R-CNN.

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. 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, boxes, output_size, spatial_scale=1.0)[source]

Performs Region of Interest (RoI) Pool operator described in Fast R-CNN

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. 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, boxes, output_size, spatial_scale=1.0)[source]

Performs Position-Sensitive Region of Interest (RoI) Pool operator described in R-FCN

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. 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, offset, weight, bias=None, stride=(1, 1), padding=(0, 0), dilation=(1, 1))[source]

Performs Deformable Convolution, described in Deformable Convolutional Networks

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

Returns

result of convolution

Return type

output (Tensor[batch_sz, out_channels, out_h, out_w])

Examples::
>>> input = torch.rand(1, 3, 10, 10)
>>> kh, kw = 3, 3
>>> weight = torch.rand(5, 3, kh, kw)
>>> # offset 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(5, 2 * kh * kw, 8, 8)
>>> out = deform_conv2d(input, offset, weight)
>>> print(out.shape)
>>> # returns
>>>  torch.Size([1, 5, 8, 8])

class torchvision.ops.RoIAlign(output_size, spatial_scale, sampling_ratio, aligned=False)[source]

See roi_align

class torchvision.ops.PSRoIAlign(output_size, spatial_scale, sampling_ratio)[source]

See ps_roi_align

class torchvision.ops.RoIPool(output_size, spatial_scale)[source]

See roi_pool

class torchvision.ops.PSRoIPool(output_size, spatial_scale)[source]

See ps_roi_pool

class torchvision.ops.DeformConv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True)[source]

See deform_conv2d

class torchvision.ops.MultiScaleRoIAlign(featmap_names, output_size, sampling_ratio)[source]

Multi-scale RoIAlign pooling, which is useful for detection with or without FPN.

It infers the scale of the pooling via the heuristics present in the FPN paper.

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

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, out_channels, extra_blocks=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]))]