MobileNet-SSD | Luxonis

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

0 Likes

Model Details

Model Description

MobileNet-SSD is an efficient and lightweight single-shot detection (SSD) model designed to perform detection of 20 common objects (background vs. aeroplane, bicycle, bird, boat, bottle, bus, car, cat, chair, cow, dining table, dog, horse, motorbike, person, potted plant, sheep, sofa, train, and tv monitor).

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

Photo by Noelle Otto from

Training Details

Training Data

Model was trained on and fine-tuned on .

Testing Details

Metrics

Accuracy was tested on . See the for more information.

Dataset	mAP [%]
VOC2007	67.00

Technical Specifications

Input:
- Name: data
  - Info: NCHW BGR image
Output:
- Name: detection_out
  - Info: Array of detections (bounding boxes, scores, labels)

Model Architecture

MobileNet backbone with the Single Shot MultiBox Detector (SSD) framework.

Throughput

Model variant: mobilenet-ssd:300x300

Platform	Precision	Throughput (infs/sec)	Power Consumption (W)
RVC2	FP16	48.76	N/A

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

* Parameters and FLOPs are obtained from the package.

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. We also have a full . So check it out!

Install DAIv3 library:

pip install depthai

Define model:

model_description = dai.NNModelDescription(
    "luxonis/mobilenet-ssd:300x300"
)

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()

NOTE: During export, normalization is added to model input (scale_values: [127.5, 127.5, 127.5], mean_values: [127.5, 127.5, 127.5]).

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/mobilenet-ssd:300x300

General object detection model.
License	MIT Commercial use
Downloads	2143
Tasks	Object Detection
Model Types	IR

Model Variants

Name	Version	Available For	Created At	Deploy
		RVC2	10 months ago