yolo-v2-tiny-tf

Use Case and High-Level Description

YOLO v2 Tiny is a real-time object detection model implemented with Keras* from this repository and converted to TensorFlow* framework. This model was pre-trained on Common Objects in Context (COCO) dataset with 80 classes.

Specification

Metric

Value

Type

Detection

GFLOPs

5.424

MParams

11.229

Source framework

Keras*

Accuracy

Accuracy metrics obtained on Common Objects in Context (COCO) validation dataset for converted model.

Metric

Value

mAP

27.34%

COCO mAP

29.11%

Input

Original model

Image, name - image_input, shape - 1, 416, 416, 3, format is B, H, W, C, where:

  • B - batch size

  • H - height

  • W - width

  • C - channel

Channel order is RGB. Scale value - 255.

Converted model

Image, name - image_input, shape - 1, 416, 416, 3, format is B, H, W, C, where:

  • B - batch size

  • H - height

  • W - width

  • C - channel

Channel order is BGR.

Output

Original model

The array of detection summary info, name - conv2d_9/BiasAdd, shape - 1, 13, 13, 425, format is B, Cx, Cy, N\*85, where:

  • B - batch size

  • Cx, Cy - cell index

  • N - number of detection boxes for cell

Detection box has format [x, y, h, w, box_score, class_no_1, …, class_no_80], where:

  • (x, y) - raw coordinates of box center, apply sigmoid function to get coordinates relative to the cell

  • h, w - raw height and width of box, apply exponential function and multiply by corresponding anchors to get height and width values relative to the cell

  • box_score - confidence of detection box, apply sigmoid function to get confidence in [0, 1] range

  • class_no_1, …, class_no_80 - probability distribution over the classes in logits format, apply softmax function and multiply by obtained confidence value to get confidence of each class

The model was trained on Common Objects in Context (COCO) dataset version with 80 categories of object. Mapping to class names provided in <omz_dir>/data/dataset_classes/coco_80cl.txt file. The anchor values are 0.57273,0.677385, 1.87446,2.06253, 3.33843,5.47434, 7.88282,3.52778, 9.77052,9.16828.

Converted model

The array of detection summary info, name - conv2d_9/BiasAdd/YoloRegion, shape - 1, 71825, which could be reshaped to 1, 425, 13, 13 with format B, N\*85, Cx, Cy, where:

  • B - batch size

  • N - number of detection boxes for cell

  • Cx, Cy - cell index

Detection box has format [x, y, h, w, box_score, class_no_1, …, class_no_80], where:

  • (x, y) - coordinates of box center relative to the cell

  • h, w - raw height and width of box, apply exponential function and multiply with corresponding anchors to get height and width values relative to the cell

  • box_score - confidence of detection box in [0, 1] range

  • class_no_1, …, class_no_80 - probability distribution over the classes in the [0, 1] range, multiply by confidence value to get confidence of each class

The model was trained on Common Objects in Context (COCO) dataset version with 80 categories of object. Mapping to class names provided in <omz_dir>/data/dataset_classes/coco_80cl.txt file. The anchor values are 0.57273,0.677385, 1.87446,2.06253, 3.33843,5.47434, 7.88282,3.52778, 9.77052,9.16828.

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: