MaxRoiPool¶
MaxRoiPool - 22¶
Version¶
name: MaxRoiPool (GitHub)
domain:
main
since_version:
22
function:
False
support_level:
SupportType.COMMON
shape inference:
True
This version of the operator has been available since version 22.
Summary¶
ROI max pool consumes an input tensor X and region of interests (RoIs) to apply max pooling across each RoI, to produce output 4-D tensor of shape (num_rois, channels, pooled_shape[0], pooled_shape[1]).
Attributes¶
pooled_shape - INTS (required) :
ROI pool output shape (height, width).
spatial_scale - FLOAT (default is
'1.0'
):Multiplicative spatial scale factor to translate ROI coordinates from their input scale to the scale used when pooling.
Inputs¶
X (heterogeneous) - T:
Input data tensor from the previous operator; dimensions for image case are (N x C x H x W), where N is the batch size, C is the number of channels, and H and W are the height and the width of the data.
rois (heterogeneous) - T:
RoIs (Regions of Interest) to pool over. Should be a 2-D tensor of shape (num_rois, 5) given as [[batch_id, x1, y1, x2, y2], …].
Outputs¶
Y (heterogeneous) - T:
RoI pooled output 4-D tensor of shape (num_rois, channels, pooled_shape[0], pooled_shape[1]).
Type Constraints¶
T in (
tensor(bfloat16)
,tensor(double)
,tensor(float)
,tensor(float16)
):Constrain input and output types to float tensors.
MaxRoiPool - 1¶
Version¶
name: MaxRoiPool (GitHub)
domain:
main
since_version:
1
function:
False
support_level:
SupportType.COMMON
shape inference:
True
This version of the operator has been available since version 1.
Summary¶
ROI max pool consumes an input tensor X and region of interests (RoIs) to apply max pooling across each RoI, to produce output 4-D tensor of shape (num_rois, channels, pooled_shape[0], pooled_shape[1]).
Attributes¶
pooled_shape - INTS (required) :
ROI pool output shape (height, width).
spatial_scale - FLOAT (default is
'1.0'
):Multiplicative spatial scale factor to translate ROI coordinates from their input scale to the scale used when pooling.
Inputs¶
X (heterogeneous) - T:
Input data tensor from the previous operator; dimensions for image case are (N x C x H x W), where N is the batch size, C is the number of channels, and H and W are the height and the width of the data.
rois (heterogeneous) - T:
RoIs (Regions of Interest) to pool over. Should be a 2-D tensor of shape (num_rois, 5) given as [[batch_id, x1, y1, x2, y2], …].
Outputs¶
Y (heterogeneous) - T:
RoI pooled output 4-D tensor of shape (num_rois, channels, pooled_shape[0], pooled_shape[1]).
Type Constraints¶
T in (
tensor(double)
,tensor(float)
,tensor(float16)
):Constrain input and output types to float tensors.