Skip to content

Instance Segmentation

Instance segmentation examples

Instance segmentation goes a step further than object detection and involves identifying individual objects in an image and segmenting them from the rest of the image.

The output of an instance segmentation model is a set of masks or contours that outline each object in the image, along with class labels and confidence scores for each object. Instance segmentation is useful when you need to know not only where objects are in an image, but also what their exact shape is.

Watch: Run Segmentation with Pre-Trained Ultralytics YOLOv8 Model in Python.


YOLOv8 Segment models use the -seg suffix, i.e. and are pretrained on COCO.


YOLOv8 pretrained Segment models are shown here. Detect, Segment and Pose models are pretrained on the COCO dataset, while Classify models are pretrained on the ImageNet dataset.

Models download automatically from the latest Ultralytics release on first use.

Model size
A100 TensorRT
YOLOv8n-seg 640 36.7 30.5 96.1 1.21 3.4 12.6
YOLOv8s-seg 640 44.6 36.8 155.7 1.47 11.8 42.6
YOLOv8m-seg 640 49.9 40.8 317.0 2.18 27.3 110.2
YOLOv8l-seg 640 52.3 42.6 572.4 2.79 46.0 220.5
YOLOv8x-seg 640 53.4 43.4 712.1 4.02 71.8 344.1
  • mAPval values are for single-model single-scale on COCO val2017 dataset.
    Reproduce by yolo val segment data=coco.yaml device=0
  • Speed averaged over COCO val images using an Amazon EC2 P4d instance.
    Reproduce by yolo val segment data=coco8-seg.yaml batch=1 device=0|cpu


Train YOLOv8n-seg on the COCO128-seg dataset for 100 epochs at image size 640. For a full list of available arguments see the Configuration page.


from ultralytics import YOLO

# Load a model
model = YOLO("yolov8n-seg.yaml")  # build a new model from YAML
model = YOLO("")  # load a pretrained model (recommended for training)
model = YOLO("yolov8n-seg.yaml").load("")  # build from YAML and transfer weights

# Train the model
results = model.train(data="coco8-seg.yaml", epochs=100, imgsz=640)
# Build a new model from YAML and start training from scratch
yolo segment train data=coco8-seg.yaml model=yolov8n-seg.yaml epochs=100 imgsz=640

# Start training from a pretrained *.pt model
yolo segment train data=coco8-seg.yaml epochs=100 imgsz=640

# Build a new model from YAML, transfer pretrained weights to it and start training
yolo segment train data=coco8-seg.yaml model=yolov8n-seg.yaml epochs=100 imgsz=640

Dataset format

YOLO segmentation dataset format can be found in detail in the Dataset Guide. To convert your existing dataset from other formats (like COCO etc.) to YOLO format, please use JSON2YOLO tool by Ultralytics.


Validate trained YOLOv8n-seg model accuracy on the COCO128-seg dataset. No argument need to passed as the model retains its training data and arguments as model attributes.


from ultralytics import YOLO

# Load a model
model = YOLO("")  # load an official model
model = YOLO("path/to/")  # load a custom model

# Validate the model
metrics = model.val()  # no arguments needed, dataset and settings remembered  # map50-95(B)  # map50(B)  # map75(B)  # a list contains map50-95(B) of each category  # map50-95(M)
metrics.seg.map50  # map50(M)
metrics.seg.map75  # map75(M)
metrics.seg.maps  # a list contains map50-95(M) of each category
yolo segment val  # val official model
yolo segment val model=path/to/  # val custom model


Use a trained YOLOv8n-seg model to run predictions on images.


from ultralytics import YOLO

# Load a model
model = YOLO("")  # load an official model
model = YOLO("path/to/")  # load a custom model

# Predict with the model
results = model("")  # predict on an image
yolo segment predict source=''  # predict with official model
yolo segment predict model=path/to/ source=''  # predict with custom model

See full predict mode details in the Predict page.


Export a YOLOv8n-seg model to a different format like ONNX, CoreML, etc.


from ultralytics import YOLO

# Load a model
model = YOLO("")  # load an official model
model = YOLO("path/to/")  # load a custom trained model

# Export the model
yolo export format=onnx  # export official model
yolo export model=path/to/ format=onnx  # export custom trained model

Available YOLOv8-seg export formats are in the table below. You can export to any format using the format argument, i.e. format='onnx' or format='engine'. You can predict or validate directly on exported models, i.e. yolo predict model=yolov8n-seg.onnx. Usage examples are shown for your model after export completes.

Format format Argument Model Metadata Arguments
PyTorch - -
TorchScript torchscript yolov8n-seg.torchscript imgsz, optimize, batch
ONNX onnx yolov8n-seg.onnx imgsz, half, dynamic, simplify, opset, batch
OpenVINO openvino yolov8n-seg_openvino_model/ imgsz, half, int8, batch
TensorRT engine yolov8n-seg.engine imgsz, half, dynamic, simplify, workspace, int8, batch
CoreML coreml yolov8n-seg.mlpackage imgsz, half, int8, nms, batch
TF SavedModel saved_model yolov8n-seg_saved_model/ imgsz, keras, int8, batch
TF GraphDef pb yolov8n-seg.pb imgsz, batch
TF Lite tflite yolov8n-seg.tflite imgsz, half, int8, batch
TF Edge TPU edgetpu yolov8n-seg_edgetpu.tflite imgsz, batch
TF.js tfjs yolov8n-seg_web_model/ imgsz, half, int8, batch
PaddlePaddle paddle yolov8n-seg_paddle_model/ imgsz, batch
NCNN ncnn yolov8n-seg_ncnn_model/ imgsz, half, batch

See full export details in the Export page.

Created 2023-11-12, Updated 2024-05-18
Authors: glenn-jocher (16), Burhan-Q (3), Laughing-q (1)