Versioned name: ExperimentalDetectronROIFeatureExtractor-6
Category: Object detection
Short description: ExperimentalDetectronROIFeatureExtractor is the ROIAlign operation applied over a feature pyramid.
Detailed description: ExperimentalDetectronROIFeatureExtractor maps input ROIs to the levels of the pyramid depending on the sizes of ROIs and parameters of the operation, and then extracts features via ROIAlign from corresponding pyramid levels.
Operation applies the ROIAlign algorithm to the pyramid layers:
output[i, :, :, :] = ROIAlign(inputPyramid[j], rois[i])
j = PyramidLevelMapper(rois[i])
PyramidLevelMapper maps the ROI to the pyramid level using the following formula:
j = floor(2 + log2(sqrt(w * h) / 224)
For more details please see the following source: Feature Pyramid Networks for Object Detection.
Attributes:
ceil(roi_width / output_width)
, and likewise for height.image_size / layer_size[l]
ratios for pyramid layers l=1,...,L
, where L
is the number of pyramid layers, and image_size
refers to network's input image. Note that pyramid's largest layer may have smaller size than input image, e.g. image_size
is 800 x 1344
in the XML example below.-0.5
) to ROIs sizes or not.true
- add offset to ROIs sizesfalse
- do not add offset to ROIs sizesInputs:
[number_of_ROIs, 4]
providing the ROIs as 4-tuples: [x1, y1, x2, y2]. Coordinates x and y are refer to the network's input image_size. Required.[1, number_of_channels, layer_size[l], layer_size[l]]
. The number of channels must be the same for all layers of the pyramid. The layer width and height must equal to the layer_size[l] = image_size / pyramid_scales[l]
. Required.Outputs:
[number_of_ROIs, number_of_channels, output_size, output_size]
. Channels number is the same as for all images in the input pyramid.[number_of_ROIs, 4]
.Types
Example