Luxonis
    Our new model ZOO works with DepthAI V3. Find out more in our documentation.
    5+ Likes
    Model Details
    Model Description
    YOLOv6n 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: Computer Vision
    • 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 .
    ModelmAPParams
    (M)
    35.94.3
    Technical Specifications
    Input/Output Details
    • Input:
      • Name: image
        • Info: NCHW BGR un-normalized image
    • Output:
      • 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-nano:r2-coco-512x288
    • Input shape: [1, 3, 288, 512] • Output shapes: [[1, 85, 36, 64], [1, 85, 18, 32], [1, 85, 9, 16]]
    • Params (M): 4.317 • GFLOPs: 2.032
    PlatformPrecisionThroughput (infs/sec)Power Consumption (W)
    RVC2FP1663.61N/A
    RVC4INT8798.383.38
    Model variant: yolov6-nano:coco-416x416
    PlatformPrecisionThroughput (infs/sec)Power Consumption (W)
    RVC2FP1667.41N/A
    * 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-nano:r2-coco-512x288"
    )
    
    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-nano:r2-coco-512x288
    
    You can also check the example with .
    Notes
    • There is a special .onnx model for RVC3 because of the unsupported reducemax operation on RVC3.
    • The post-processing operations were pruned. For RVC3, the objectness tensor is set to ones because of the unsupported reducemax operation on RVC3.
    YOLOv6 Nano
    General object Detection model
    License
    GNU General Public License v3.0
    Commercial use
    Downloads
    83566
    Tasks
    Object Detection
    Model Types
    IR
    ONNX
    Model Variants
    NameVersionAvailable ForCreated AtDeploy
    RVC211 months ago
    RVC3About 1 year ago
    RVC2, RVC4About 1 year ago
    Luxonis - Robotic vision made simple.
    XYouTubeLinkedInGitHub