QRDet | Luxonis

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

0 Likes

Model Details

Model Description

QRDet is a YOLOv8 based convolutional neural network model designed for QR Code detection. It is highly effective and accurate even for more tricky images. We implement here the nano version of the model.

Developed by: Eric Cañas
Shared by:
Model type: Computer Vision
License:
Resources for more information:

Photo by Erik Mclean from

Training Details

Training Data

No data available.

Testing Details

Metrics

No data available.

Technical Specifications

Input:
- Name: images
  - Info: BGR image
Output1:
- Name: output1_yolov6r2
  - Info: Detection output 1
Output2:
- Name: output2_yolov6r2
  - Info: Detection output 2
Output3:
- Name: output3_yolov6r2
  - Info: Detection output 3

Model Architecture

Backbone: CSPDarknet53
Neck: Path Aggregation Network (PANet)
Head: Anchor-free object detection head (pruned of concatenation)

Consult the for more information.

Throughput

Model variant: qrdet:nano-512x288

• Input shape: [1, 3, 288, 512] • Output shapes: [[1, 6, 36, 64], [1, 6, 18, 32], [1, 6, 9, 16]]

• Params (M): 3.006 • GFLOPs: 1.631

Platform	Precision	Throughput (infs/sec)	Power Consumption (W)
RVC2	FP16	34.52	N/A
RVC4	INT8	701.34	3.73

* 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 50-image subset of the dataset made publicli available over Roboflow by Capstone Project.

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/qrdet:nano-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 and scores of the detected QR codes).

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/qrdet:nano-512x288

QR code detection model.
License	MIT Commercial use
Downloads	279
Tasks	Object Detection
Model Types	ONNX

Model Variants

Name	Version	Available For	Created At	Deploy
		RVC2, RVC4	11 months ago