This is a re-trained version of Faster R-CNN object detection network trained with 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 BGR order. The pixel values are integers in the [0, 255] range.
|Mean Average Precision (mAP)||38.74%**|
Average Precision metric described in: "COCO: Common Objects in Context". The primary challenge metric is used. Tested on COCO validation dataset.
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 deteciton is on
y0) - normalized coordinates of the top left bounding box corner, in range of [0, 1]
y1) - normalized coordinates of the bootm right bounding box corner, in range of [0, 1].
[*] Other names and brands may be claimed as the property of others.
[**] May be different from the original implementation due to different input configurations.