ngraph.psroi_pooling¶
- ngraph.psroi_pooling(input: Union[_pyngraph.Node, int, float, numpy.ndarray], coords: Union[_pyngraph.Node, int, float, numpy.ndarray], output_dim: int, group_size: int, spatial_scale: float, spatial_bins_x: int, spatial_bins_y: int, mode: str, name: Optional[str] = None) _pyngraph.Node¶
Return a node which produces a PSROIPooling operation.
- Parameters
input – Input feature map {N, C, …}
coords – Coordinates of bounding boxes
output_dim – Output channel number
group_size – Number of groups to encode position-sensitive scores
spatial_scale – Ratio of input feature map over input image size
spatial_bins_x – Numbers of bins to divide the input feature maps over
spatial_bins_y – Numbers of bins to divide the input feature maps over
mode – Mode of pooling - “avg” or “bilinear”
- Returns
PSROIPooling node