This is a retrained version of the Faster R-CNN object detection network trained with the COCO* training dataset. The actual implementation is based on Detectron, with additional network weight pruning applied to sparsify convolution layers (60% of network parameters are set to zeros).
The model input is a blob that consists of a single image of
1x3x800x1280 in the BGR order. The pixel values are integers in the [0, 255] range.
|Mean Average Precision (mAP)||38.74%**|
See Average Precision metric description at COCO: Common Objects in Context. The primary challenge metric is used. Tested on the COCO validation dataset.
input, shape: [1x3x800x1280] - An input image in the format [BxCxHxW], where:
The net outputs a blob with the shape [300, 7], where each row consists of [
image_id- image ID in the batch
class_id- predicted class ID
confidence- [0, 1] detection score; the higher the value, the more confident the detection is
y0) - normalized coordinates of the top left bounding box corner, in the [0, 1] range
y1) - normalized coordinates of the bottom right bounding box corner, in the [0, 1] range
[*] Other names and brands may be claimed as the property of others.
[**] May be different from the original implementation due to different input configurations.