yolo-v4-tf

Use Case and High-Level Description

YOLO v4 is a real-time object detection model based on “YOLOv4: Optimal Speed and Accuracy of Object Detection” paper. It was implemented in Keras* framework and converted to TensorFlow* framework. For details see repository. This model was pre-trained on Common Objects in Context (COCO) dataset with 80 classes.

Specification

Metric

Value

Type

Detection

GFLOPs

129.5567

MParams

64.33

Source framework

Keras*

Accuracy

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

Metric

Value

mAP

71.23%

COCO mAP (0.5)

77.40%

COCO mAP (0.5:0.05:0.95)

50.26%

Input

Original model

Image, name - image_input, shape - 1, 608, 608, 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, 608, 608, 3, format is B, H, W, C, where:

  • B - batch size

  • H - height

  • W - width

  • C - channel

Channel order is BGR.

Output

Original model

  1. The array of detection summary info, name - conv2d_93/BiasAdd, shape - 1, 76, 76, 255. The anchor values are 12,16, 19,36, 40,28.

  2. The array of detection summary info, name - conv2d_101/BiasAdd, shape - 1, 38, 38, 255. The anchor values are 36,75, 76,55, 72,146.

  3. The array of detection summary info, name - conv2d_109/BiasAdd, shape - 1, 19, 19, 255. The anchor values are 142,110, 192,243, 459,401.

For each case 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 relative to the cell coordinates

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

  • 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 sigmoid 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.

Converted model

  1. The array of detection summary info, name - StatefulPartitionedCall/model/conv2d_93/BiasAdd/Add, shape - 1, 76, 76, 255. The anchor values are 12,16, 19,36, 40,28.

  2. The array of detection summary info, name - StatefulPartitionedCall/model/conv2d_101/BiasAdd/Add, shape - 1, 38, 38, 255. The anchor values are 36,75, 76,55, 72,146.

  3. The array of detection summary info, name - StatefulPartitionedCall/model/conv2d_109/BiasAdd/Add, shape - 1, 19, 19, 255. The anchor values are 142,110, 192,243, 459,401.

For each case format is B, Cx, Cy, N\*85, 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) - raw coordinates of box center, apply sigmoid function to get relative to the cell coordinates

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

  • 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 sigmoid 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.

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: