Use Case and High-Level Description

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.


Metric Value
Mean Average Precision (mAP) 38.74%**
Flops 364.21Bn
MParams 52.79
Source framework TensorFlow*

See Average Precision metric description at COCO: Common Objects in Context. The primary challenge metric is used. Tested on the COCO validation dataset.



Name: 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, class_id, confidence, x0, y0, x1, y1] respectively:

Legal Information

[*] Other names and brands may be claimed as the property of others.

[**] May be different from the original implementation due to different input configurations.