<dd>Features with shape [N,4C,H,W]. Channels ranged in [0,C), [C,2C), [2C,3C), [3C,4C) represent the top, left, bottom, right features respectively</dd>
<dt><tt>boxes</tt>: T</dt>
<dd>Boxes with shape [N,H*W,4]. Coordinate format (x1,y1,x2,y2).</dd>
</dl>
### Outputs
<dl>
<dt><tt>output</tt>: T</dt>
<dd>Pooled features with shape [N,C,H*W,4]. The order is(top,left,bottom,right) for the last dimension.</dd>
</dl>
### Type Constraints
- T:tensor(float32)
## MMCVCARAFE
### Description
CARAFE operator performs feature upsampling.
Read [CARAFE: Content-Aware ReAssembly of FEatures](https://arxiv.org/abs/1905.02188) for more detailed information.
<dd>Input feature; 4-D tensor of shape (N, C, inH, inW), where N is the batch size, C is the number of channels, inH and inW are the height and width of the data.</dd>
<dt><tt>offset</tt>: T</dt>
<dd>Input offset; 4-D tensor of shape (N, deformable_group* 2* kH* kW, outH, outW), where kH and kW are the height and width of weight, outH and outW is the height and width of offset and output.</dd>
<dt><tt>weight</tt>: T</dt>
<dd>Input weight; 4-D tensor of shape (output_channel, input_channel, kH, kW).</dd>
</dl>
### Outputs
<dl>
<dt><tt>output</tt>: T</dt>
<dd>Output feature; 4-D tensor of shape (N, output_channel, outH, outW).</dd>
</dl>
### Type Constraints
- T:tensor(float32, Linear)
## MMCVModulatedDeformConv2d
### Description
Perform Modulated Deformable Convolution on input feature, read [Deformable ConvNets v2: More Deformable, Better Results](https://arxiv.org/abs/1811.11168?from=timeline) for detail.
| `int` | `deformable_groups` | Groups of deformable offset. |
| `int` | `groups` | Split input into groups. `input_channel` should be divisible by the number of groups. |
### Inputs
<dl>
<dt><tt>feature</tt>: T</dt>
<dd>Input feature; 4-D tensor of shape (N, C, inH, inW), where N is the batch size, C is the number of channels, inH and inW are the height and width of the data.</dd>
<dt><tt>offset</tt>: T</dt>
<dd>Input offset; 4-D tensor of shape (N, deformable_group* 2* kH* kW, outH, outW), where kH and kW are the height and width of weight, outH and outW are the height and width of offset and output.</dd>
<dt><tt>mask</tt>: T</dt>
<dd>Input mask; 4-D tensor of shape (N, deformable_group* kH* kW, outH, outW), where kH and kW are the height and width of weight, outH and outW are the height and width of offset and output.</dd>
<dt><tt>weight]</tt>: T</dt>
<dd>Input weight; 4-D tensor of shape (output_channel, input_channel, kH, kW).</dd>
<dt><tt>bias</tt>: T, optional</dt>
<dd>Input bias; 1-D tensor of shape (output_channel).</dd>
</dl>
### Outputs
<dl>
<dt><tt>output</tt>: T</dt>
<dd>Output feature; 4-D tensor of shape (N, output_channel, outH, outW).</dd>
<dd>Input feature map; 4D tensor of shape (N, C, H, W), where N is the batch size, C is the numbers of channels, H and W are the height and width of the data.</dd>
<dt><tt>rois</tt>: T</dt>
<dd>RoIs (Regions of Interest) to pool over; 2-D tensor of shape (num_rois, 5) given as [[batch_index, x1, y1, x2, y2], ...]. The RoIs' coordinates are the coordinate system of input.</dd>
<dt><tt>offset</tt>: T</dt>
<dd>offset of height and width. Defaults to a tensor of zero</dd>
</dl>
### Outputs
<dl>
<dt><tt>feat</tt>: T</dt>
<dd>RoI pooled output, 4-D tensor of shape (num_rois, C, output_height, output_width). The r-th batch element feat[r-1] is a pooled feature map corresponding to the r-th RoI RoIs[r-1].<dd>
</dl>
### Type Constraints
- T:tensor(float32)
## MMCVMaskedConv2d
### Description
Performs a masked 2D convolution from PixelRNN
Read [Pixel Recurrent Neural Networks](https://arxiv.org/abs/1601.06759) for more detailed information.
<dd>Input features; 4D tensor of shape (N, C, H, W), where N is the batch size, C is the numbers of channels, H and W are the height and width of the data.</dd>
<dt><tt>mask</tt>: T</dt>
<dd>Input mask; 3D tensor of shape (N, H, W)</dd>
<dt><tt>weight</tt>: T</dt>
<dd>The learnable weights of the module</dd>
<dt><tt>bias</tt>: T</dt>
<dd>The learnable bias of the module</dd>
</dl>
### Outputs
<dl>
<dt><tt>output</tt>: T</dt>
<dd>The output convolved feature</dd>
</dl>
### Type Constraints
- T:tensor(float32)
## MMCVPSAMask
### Description
An operator from PSANet.
Read [PSANet: Point-wise Spatial Attention Network for Scene Parsing](https://hszhao.github.io/papers/eccv18_psanet.pdf) for more detailed information.
<dd>Input feature; 4D tensor of shape (N, C, H, W), where N is the batch size, C is the numbers of channels, H and W are the height and width of the data.</dd>
</dl>
### Outputs
<dl>
<dt><tt>output</tt>: T</dt>
<dd>Output tensor of shape (N, H * W, H, W)</dd>
</dl>
### Type Constraints
- T:tensor(float32)
## NonMaxSuppression
### Description
Filter out boxes has high IoU overlap with previously selected boxes or low score. Output the indices of valid boxes.
Note this definition is slightly different with [onnx: NonMaxSuppression](https://github.com/onnx/onnx/blob/master/docs/Operators.md#nonmaxsuppression)
| `int` | `center_point_box` | 0 - the box data is supplied as \[y1, x1, y2, x2\], 1-the box data is supplied as \[x_center, y_center, width, height\]. |
| `int` | `max_output_boxes_per_class` | The maximum number of boxes to be selected per batch per class. Default to 0, number of output boxes equal to number of input boxes. |
| `int` | `output_height` | height of output roi |
| `int` | `output_width` | width of output roi |
| `float` | `spatial_scale` | used to scale the input boxes |
| `int` | `sampling_ratio` | number of input samples to take for each output sample. `0` means to take samples densely for current models. |
| `str` | `mode` | pooling mode in each bin. `avg` or `max` |
| `int` | `aligned` | If `aligned=0`, use the legacy implementation in MMDetection. Else, align the results more perfectly. |
### Inputs
<dl>
<dt><tt>input</tt>: T</dt>
<dd>Input feature map; 4D tensor of shape (N, C, H, W), where N is the batch size, C is the numbers of channels, H and W are the height and width of the data.</dd>
<dt><tt>rois</tt>: T</dt>
<dd>RoIs (Regions of Interest) to pool over; 2-D tensor of shape (num_rois, 5) given as [[batch_index, x1, y1, x2, y2], ...]. The RoIs' coordinates are the coordinate system of input.</dd>
</dl>
### Outputs
<dl>
<dt><tt>feat</tt>: T</dt>
<dd>RoI pooled output, 4-D tensor of shape (num_rois, C, output_height, output_width). The r-th batch element feat[r-1] is a pooled feature map corresponding to the r-th RoI RoIs[r-1].<dd>
<dd>RoIs (Regions of Interest) to pool over; 2-D tensor of shape (num_rois, 5) given as [[batch_index, x1, y1, x2, y2], ...]. The RoIs' coordinates are the coordinate system of input.</dd>
</dl>
### Outputs
<dl>
<dd>RoI pooled output, 4-D tensor of shape (num_rois, C, output_height, output_width). The r-th batch element feat[r-1] is a pooled feature map corresponding to the r-th RoI RoIs[r-1].<dd>
Perform sample from `input` with pixel locations from `grid`.
Check [torch.nn.functional.grid_sample](https://pytorch.org/docs/stable/generated/torch.nn.functional.grid_sample.html?highlight=grid_sample#torch.nn.functional.grid_sample) for more information.
| `int` | `align_corners` | If `align_corners=1`, the extrema (`-1` and `1`) are considered as referring to the center points of the input's corner pixels. If `align_corners=0`, they are instead considered as referring to the corner points of the input's corner pixels, making the sampling more resolution agnostic. |
### Inputs
<dl>
<dt><tt>input</tt>: T</dt>
<dd>Input feature; 4-D tensor of shape (N, C, inH, inW), where N is the batch size, C is the numbers of channels, inH and inW are the height and width of the data.</dd>
<dt><tt>grid</tt>: T</dt>
<dd>Input offset; 4-D tensor of shape (N, outH, outW, 2), where outH and outW are the height and width of offset and output. </dd>
</dl>
### Outputs
<dl>
<dt><tt>output</tt>: T</dt>
<dd>Output feature; 4-D tensor of shape (N, C, outH, outW).</dd>
Returns a tuple (`values`, `indices`) where `values` is the cumulative maximum elements of `input` in the dimension `dim`. And `indices` is the index location of each maximum value found in the dimension `dim`. Read [torch.cummax](https://pytorch.org/docs/stable/generated/torch.cummax.html) for more details.
Returns a tuple (`values`, `indices`) where `values` is the cumulative minimum elements of `input` in the dimension `dim`. And `indices` is the index location of each minimum value found in the dimension `dim`. Read [torch.cummin](https://pytorch.org/docs/stable/generated/torch.cummin.html) for more details.
