ctdet_coco_dlav0_512

Use Case and High-Level Description

CenterNet object detection model ctdet_coco_dlav0_512 originally trained with PyTorch*. CenterNet models an object as a single point - the center point of its bounding box and uses keypoint estimation to find center points and regresses to object size. For details see paper, repository.

Specification

Metric

Value

Type

Detection

GFlops

62.211

MParams

17.911

Source framework

PyTorch*

Accuracy

Metric

Original model

Converted model

mAP

44.2%

44.28%

Input

Original Model

Image, name: input.1, shape: 1, 3, 512, 512, format: B, C, H, W, where:

  • B - batch size

  • C - number of channels

  • H - image height

  • W - image width

Expected color order: BGR. Mean values: [104.04, 113.985, 119.85], scale values: [73.695, 69.87, 70.89].

Converted Model

Image, name: input.1, shape: 1, 3, 512, 512, format: B, C, H, W, where:

  • B - batch size

  • C - number of channels

  • H - image height

  • W - image width

Expected color order: BGR.

Output

  1. Object center points heatmap, name: center_heatmap. Contains predicted objects center point, for each of the 80 categories, according to Common Objects in Context (COCO) dataset version with 80 categories of objects, without background label, mapping to class names provided in <omz_dir>/data/dataset_classes/coco_80cl.txt file.

  2. Object size output, name: width_height. Contains predicted width and height for each object.

  3. Regression output, name: regression. Contains offsets for each prediction.

Download a Model and Convert it into OpenVINO™ IR Format

You can download models and if necessary convert them into OpenVINO™ IR format using the Model Downloader and other automation tools as shown in the examples below.

An example of using the Model Downloader:

omz_downloader --name <model_name>

An example of using the Model Converter:

omz_converter --name <model_name>

Demo usage

The model can be used in the following demos provided by the Open Model Zoo to show its capabilities: