yolo-v3-onnx¶
Use Case and High-Level Description¶
YOLO v3 is a real-time object detection model in ONNX* format from the repository which is converted from Keras* model repository using keras2onnx converter. This model was pre-trained on Common Objects in Context (COCO) dataset with 80 classes.
Specification¶
Metric |
Value |
---|---|
Type |
Detection |
GFLOPs |
65.998 |
MParams |
61.930 |
Source framework |
ONNX* |
Accuracy¶
Accuracy metrics obtained on Common Objects in Context (COCO) validation dataset for converted model.
Metric |
Value |
---|---|
mAP |
48.30% |
47.07% |
Input¶
Original model¶
Image, name -
input_1
, shape -1, 3, 416, 416
, format isB, C, H, W
, where:B
- batch sizeC
- channelH
- heightW
- width
Channel order is
RGB
. Scale value - 255.Information of input image size, name:
image_shape
, shape:1, 2
, format:B, C
, where:B
- batch sizeC
- vector of 2 values in formatH, W
, whereH
is an image height,W
is an image width.
Converted model¶
Image, name -
input_1
, shape -1, 3, 416, 416
, format isB, C, H, W
, where:B
- batch sizeC
- channelH
- heightW
- width
Channel order is
BGR
.Information of input image size, name:
image_shape
, shape:1, 2
, format:B, C
, where:B
- batch sizeC
- vector of 2 values in formatH, W
, whereH
is an image height,W
is an image width.
Output¶
Original model¶
Boxes coordinates, name -
yolonms_layer_1/ExpandDims_1:0
, shape -1, 10647, 4
, format -B, N, 4
, where:B
- batch sizeN
- number of candidates
Scores of boxes per class, name -
yolonms_layer_1/ExpandDims_3:0
, shape -1, 80, 10647
, format -B, 80, N
, where:B
- batch sizeN
- number of candidates
Selected indices from the boxes tensor, name -
yolonms_layer_1/concat_2:0
, shape -1, 1600, 3
, format -B, N, 3
, where:B
- batch sizeN
- number of detection boxes
Each index has format [b_idx
, cls_idx
, box_idx
], where:
b_idx
- batch indexcls_idx
- class_indexbox_idx
- box_index
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¶
Boxes coordinates, name -
yolonms_layer_1/ExpandDims_1:0
, shape -1, 10647, 4
, format -B, N, 4
, where:B
- batch sizeN
- number of candidates
Scores of boxes per class, name -
yolonms_layer_1/ExpandDims_3:0
, shape -1, 80, 10647
, format -B, 80, N
, where:B
- batch sizeN
- number of candidates
Selected indices from the boxes tensor, name -
yolonms_layer_1/concat_2:0
, shape -1, 1600, 3
, format -B, N, 3
, where:B
- batch sizeN
- number of detection boxes
Each index has format [b_idx
, cls_idx
, box_idx
], where:
b_idx
- batch indexcls_idx
- class_indexbox_idx
- box_index
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:
Legal Information¶
The original model is distributed under the Apache License, Version 2.0. A copy of the license is provided in <omz_dir>/models/public/licenses/APACHE-2.0.txt
.