YOLOv6 Large | Luxonis

Our new model ZOO works with DepthAI V3. Find out more in our documentation.

0 Likes

Model Details

Model Description

YOLOv6l model is a convolutional neural network designed for object detection. It is highly effective and accurate, making it ideal for real-time applications on edge devices. It was trained on the COCO data set. It is capable of detecting objects of 80 classes.

Developed by: Meituan Vision AI Department
Shared by:
Model type: Object detection model
License:
Resources for more information:

Training Details

Training Data

is a large-scale object detection, segmentation, and captioning dataset.

Testing Details

Metrics

Results of the mAP and speed are evaluated on COCO val2017 dataset with the input resolution of 640×640. Results are taken from .

Model	mAP	Params ^(M)
	52.5	58.5

Technical Specifications

Input/Output Details

Input:
- Name: image
  - Info: NCHW BGR un-normalized image
Outputs:
- Name: output1_yolov6r2
  - Info: Unprocessed output of the first channel
- Name: output2_yolov6r2
  - Info: Unprocessed output of the second channel
- Name: output3_yolov6r2
  - Info: Unprocessed output of the third channel

Model Architecture

Backbone: EfficientRep backbone
Neck: Rep-PAN neck
Head: Efficient decoupled head that is anchor-free

Please consult the for more information on model architecture.

Throughput

Model variant: yolov6-large:r2-coco-640x352

• Input shape: [1, 3, 352, 640] • Output shapes: [[1, 85, 44, 80], [1, 85, 22, 40], [1, 85, 11, 20]]

• Params (M): 58.541 • GFLOPs: 41.022

Platform	Precision	Throughput (infs/sec)	Power Consumption (W)
RVC4	INT8	165.14	5.87

* Benchmarked with , using 2 threads (and the DSP runtime in balanced mode for RVC4).

* Parameters and FLOPs are obtained from the package.

Quantization

RVC4 version of the model was quantized using a custom dataset. This was created by taking a full 128-image dataset.

Utilization

Models converted for RVC Platforms can be used for inference on OAK devices. DepthAI pipelines are used to define the information flow linking the device, inference model, and the output parser (as defined in model head(s)). Below, we present the most crucial utilization steps for the particular model. Please consult the docs for more information.

Install DAIv3 library:

pip install depthai

Define model:

model_description = dai.NNModelDescription(
    "luxonis/yolov6-large:r2-coco-640x352"
)

nn = pipeline.create(dai.node.DetectionNetwork).build(
    <CameraNode>, model_description
)

The model is automatically parsed by DAI and it outputs the message (bounding boxes, labels, and scores of the detected objects).

Get model output(s):

while pipeline.isRuning():
    nn_output: dai.ImgDetections = parser_output_queue.get()

Example

You can quickly run the model using our script. It automatically downloads the model, creates a DepthAI pipeline, runs the inference, and displays the results using our DepthAI visualizer tool. To try it out, run:

python3 main.py \
    --model luxonis/yolov6-large:r2-coco-640x352

General object Detection model
License	GNU General Public License v3.0 Commercial use
Downloads	3598
Tasks	Object Detection
Model Types	ONNX

Model Variants

Name	Version	Available For	Created At	Deploy
		RVC4	11 months ago