YOLOv8-16bit/docs/tasks/pose.md

comments	description	keywords
true	Learn how to use YOLOv8 pose estimation models to identify the position of keypoints on objects in an image, and how to train, validate, predict, and export these models for use with various formats such as ONNX or CoreML.	YOLOv8, Pose Models, Keypoint Detection, COCO dataset, COCO val2017, Amazon EC2 P4d, PyTorch

Pose estimation is a task that involves identifying the location of specific points in an image, usually referred to as keypoints. The keypoints can represent various parts of the object such as joints, landmarks, or other distinctive features. The locations of the keypoints are usually represented as a set of 2D [x, y] or 3D [x, y, visible] coordinates.

The output of a pose estimation model is a set of points that represent the keypoints on an object in the image, usually along with the confidence scores for each point. Pose estimation is a good choice when you need to identify specific parts of an object in a scene, and their location in relation to each other.

!!! tip "Tip"

YOLOv8 _pose_ models use the `-pose` suffix, i.e. `yolov8n-pose.pt`. These models are trained on the [COCO keypoints](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/datasets/coco-pose.yaml) dataset and are suitable for a variety of pose estimation tasks.

Models

YOLOv8 pretrained Pose 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 (pixels)	mAPpose 50-95	mAPpose 50	Speed CPU ONNX (ms)	Speed A100 TensorRT (ms)	params (M)	FLOPs (B)
YOLOv8n-pose	640	50.4	80.1	131.8	1.18	3.3	9.2
YOLOv8s-pose	640	60.0	86.2	233.2	1.42	11.6	30.2
YOLOv8m-pose	640	65.0	88.8	456.3	2.00	26.4	81.0
YOLOv8l-pose	640	67.6	90.0	784.5	2.59	44.4	168.6
YOLOv8x-pose	640	69.2	90.2	1607.1	3.73	69.4	263.2
YOLOv8x-pose-p6	1280	71.6	91.2	4088.7	10.04	99.1	1066.4

• mAP^val values are for single-model single-scale on COCO Keypoints val2017 dataset.
  Reproduce by yolo val pose data=coco-pose.yaml device=0
• Speed averaged over COCO val images using an Amazon EC2 P4d instance.
  Reproduce by yolo val pose data=coco8-pose.yaml batch=1 device=0|cpu

Train

Train a YOLOv8-pose model on the COCO128-pose dataset.

!!! example ""

=== "Python"

    ```python
    from ultralytics import YOLO
    
    # Load a model
    model = YOLO('yolov8n-pose.yaml')  # build a new model from YAML
    model = YOLO('yolov8n-pose.pt')  # load a pretrained model (recommended for training)
    model = YOLO('yolov8n-pose.yaml').load('yolov8n-pose.pt')  # build from YAML and transfer weights
    
    # Train the model
    model.train(data='coco8-pose.yaml', epochs=100, imgsz=640)
    ```
=== "CLI"

    ```bash
    # Build a new model from YAML and start training from scratch
    yolo pose train data=coco8-pose.yaml model=yolov8n-pose.yaml epochs=100 imgsz=640

    # Start training from a pretrained *.pt model
    yolo pose train data=coco8-pose.yaml model=yolov8n-pose.pt epochs=100 imgsz=640

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

Dataset format

YOLO pose 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.

Val

Validate trained YOLOv8n-pose model accuracy on the COCO128-pose dataset. No argument need to passed as the model retains it's training data and arguments as model attributes.

!!! example ""

=== "Python"

    ```python
    from ultralytics import YOLO
    
    # Load a model
    model = YOLO('yolov8n-pose.pt')  # load an official model
    model = YOLO('path/to/best.pt')  # load a custom model
    
    # Validate the model
    metrics = model.val()  # no arguments needed, dataset and settings remembered
    metrics.box.map    # map50-95
    metrics.box.map50  # map50
    metrics.box.map75  # map75
    metrics.box.maps   # a list contains map50-95 of each category
    ```
=== "CLI"

    ```bash
    yolo pose val model=yolov8n-pose.pt  # val official model
    yolo pose val model=path/to/best.pt  # val custom model
    ```

Predict

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

!!! example ""

=== "Python"

    ```python
    from ultralytics import YOLO
    
    # Load a model
    model = YOLO('yolov8n-pose.pt')  # load an official model
    model = YOLO('path/to/best.pt')  # load a custom model
    
    # Predict with the model
    results = model('https://ultralytics.com/images/bus.jpg')  # predict on an image
    ```
=== "CLI"

    ```bash
    yolo pose predict model=yolov8n-pose.pt source='https://ultralytics.com/images/bus.jpg'  # predict with official model
    yolo pose predict model=path/to/best.pt source='https://ultralytics.com/images/bus.jpg'  # predict with custom model
    ```

See full predict mode details in the Predict page.

Export

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

!!! example ""

=== "Python"

    ```python
    from ultralytics import YOLO
    
    # Load a model
    model = YOLO('yolov8n-pose.pt')  # load an official model
    model = YOLO('path/to/best.pt')  # load a custom trained
    
    # Export the model
    model.export(format='onnx')
    ```
=== "CLI"

    ```bash
    yolo export model=yolov8n-pose.pt format=onnx  # export official model
    yolo export model=path/to/best.pt format=onnx  # export custom trained model
    ```

Available YOLOv8-pose export formats are in the table below. You can predict or validate directly on exported models, i.e. yolo predict model=yolov8n-pose.onnx. Usage examples are shown for your model after export completes.

Format	format Argument	Model	Metadata	Arguments
PyTorch	-	yolov8n-pose.pt	✅	-
TorchScript	torchscript	yolov8n-pose.torchscript	✅	imgsz, optimize
ONNX	onnx	yolov8n-pose.onnx	✅	imgsz, half, dynamic, simplify, opset
OpenVINO	openvino	yolov8n-pose_openvino_model/	✅	imgsz, half
TensorRT	engine	yolov8n-pose.engine	✅	imgsz, half, dynamic, simplify, workspace
CoreML	coreml	yolov8n-pose.mlmodel	✅	imgsz, half, int8, nms
TF SavedModel	saved_model	yolov8n-pose_saved_model/	✅	imgsz, keras
TF GraphDef	pb	yolov8n-pose.pb	❌	imgsz
TF Lite	tflite	yolov8n-pose.tflite	✅	imgsz, half, int8
TF Edge TPU	edgetpu	yolov8n-pose_edgetpu.tflite	✅	imgsz
TF.js	tfjs	yolov8n-pose_web_model/	✅	imgsz
PaddlePaddle	paddle	yolov8n-pose_paddle_model/	✅	imgsz
NCNN	ncnn	yolov8n-pose_ncnn_model/	✅	imgsz

See full export details in the Export page.