X

Name	Version	Available For	Created At	Deploy
		RVC2, RVC4	About 1 year ago

Model Details

Model Description

YOLOv8 Instance Segmentation is a YOLOv8 based convolutional neural network model designed for identifying individual objects in an image and segmenting them from the rest of the image. It is highly effective and accurate even for more tricky images. We implement here the nano version of the model.

Developed by: Ultralytics
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 dataset with the input resolution of 640×640. Results are taken from .

Model	mAP (box)	mAP (mask)	Params ^(M)
	36.7	30.5	3.4

Technical Specifications

Input/Output Details

Input:
- Name: image
  - Info: NCHW BGR un-normalized image
Outputs:
- Name: Multiple (please consult NN archive config.json)
  - Info: Unprocessed outputs of a multitude of detections, masks and protos

Model Architecture

Backbone: CSPDarknet53
Head: Anchor-free object segmentation head (pruned of concatenation)

Consult the for more information.

Throughput

Model variant: yolov8-instance-segmentation-nano:coco-512x288

• Input shape: [1, 3, 288, 512] • Output shapes: [[1, 85, 36, 64], [1, 85, 18, 32], [1, 85, 9, 16], [1, 32, 36, 64], [1, 32, 18, 32], [1, 32, 9, 16], [1, 32, 72, 128]]

• Params (M): 3.404 • GFLOPs: 2.503

Platform	Precision	Throughput (infs/sec)	Power Consumption (W)
RVC2	FP16	27.28	N/A
RVC4	INT8	531.60	3.64

* 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 and depthai-nodes libraries:

pip install depthai
pip install depthai-nodes

Define model:

model_description = dai.NNModelDescription(
    "luxonis/yolov8-instance-segmentation-nano:coco-512x288"
)

nn = pipeline.create(ParsingNeuralNetwork).build(
    <CameraNode>, model_description
)

Inspect model head(s):

YOLOExtendedParser that outputs message (bounding boxes and segmentation masks of detected objects).

Get parsed output(s):

while pipeline.isRuning():
    parser_output: ImgDetectionsExtended = 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/yolov8-instance-segmentation-nano:coco-512x288 \
    -overlay

General instance segmentation model.
License	GNU Affero General Public License v3.0 Commercial use
Downloads	974
Tasks	Semantic Segmentation
Model Types	ONNX