diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index 29a5387..947bd24 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -43,21 +43,7 @@ jobs:
python --version
pip --version
pip list
- - name: Test HUB training (Python Usage 1)
- shell: python
- env:
- APIKEY: ${{ secrets.ULTRALYTICS_HUB_APIKEY }}
- run: |
- import os
- from pathlib import Path
- from ultralytics import YOLO, hub
- from ultralytics.yolo.utils import USER_CONFIG_DIR
- Path(USER_CONFIG_DIR / 'settings.yaml').unlink()
- key = os.environ['APIKEY']
- hub.reset_model(key)
- model = YOLO('https://hub.ultralytics.com/models/' + key)
- model.train()
- - name: Test HUB training (Python Usage 2)
+ - name: Test HUB training
shell: python
env:
APIKEY: ${{ secrets.ULTRALYTICS_HUB_APIKEY }}
@@ -73,36 +59,6 @@ jobs:
hub.login(key)
model = YOLO('https://hub.ultralytics.com/models/' + model_id)
model.train()
- - name: Test HUB training (Python Usage 3)
- shell: python
- env:
- APIKEY: ${{ secrets.ULTRALYTICS_HUB_APIKEY }}
- run: |
- import os
- from pathlib import Path
- from ultralytics import YOLO, hub
- from ultralytics.yolo.utils import USER_CONFIG_DIR
- Path(USER_CONFIG_DIR / 'settings.yaml').unlink()
- key = os.environ['APIKEY']
- hub.reset_model(key)
- model = YOLO(key)
- model.train()
- - name: Test HUB training (Python Usage 4)
- shell: python
- env:
- APIKEY: ${{ secrets.ULTRALYTICS_HUB_APIKEY }}
- run: |
- import os
- from pathlib import Path
- from ultralytics import YOLO, hub
- from ultralytics.yolo.utils import USER_CONFIG_DIR
- Path(USER_CONFIG_DIR / 'settings.yaml').unlink()
- key = os.environ['APIKEY']
- hub.reset_model(key)
- key, model_id = key.split('_')
- hub.login(key)
- model = YOLO(model_id)
- model.train()
Benchmarks:
runs-on: ${{ matrix.os }}
@@ -154,6 +110,11 @@ jobs:
run: |
from ultralytics.yolo.utils.benchmarks import benchmark
benchmark(model='${{ matrix.model }}-cls.pt', imgsz=160, half=False, hard_fail=0.61)
+ - name: Benchmark PoseModel
+ shell: python
+ run: |
+ from ultralytics.yolo.utils.benchmarks import benchmark
+ benchmark(model='${{ matrix.model }}-pose.pt', imgsz=160, half=False, hard_fail=0.0)
- name: Benchmark Summary
run: |
cat benchmarks.log
@@ -200,30 +161,38 @@ jobs:
python --version
pip --version
pip list
- - name: Test detection
+ - name: Test Detect
+ shell: bash # for Windows compatibility
+ run: |
+ yolo detect train data=coco8.yaml model=yolov8n.yaml epochs=1 imgsz=32
+ yolo detect train data=coco8.yaml model=yolov8n.pt epochs=1 imgsz=32
+ yolo detect val data=coco8.yaml model=runs/detect/train/weights/last.pt imgsz=32
+ yolo detect predict model=runs/detect/train/weights/last.pt imgsz=32 source=ultralytics/assets/bus.jpg
+ yolo export model=runs/detect/train/weights/last.pt imgsz=32 format=torchscript
+ - name: Test Segment
shell: bash # for Windows compatibility
run: |
- yolo task=detect mode=train data=coco8.yaml model=yolov8n.yaml epochs=1 imgsz=32
- yolo task=detect mode=train data=coco8.yaml model=yolov8n.pt epochs=1 imgsz=32
- yolo task=detect mode=val data=coco8.yaml model=runs/detect/train/weights/last.pt imgsz=32
- yolo task=detect mode=predict model=runs/detect/train/weights/last.pt imgsz=32 source=ultralytics/assets/bus.jpg
- yolo mode=export model=runs/detect/train/weights/last.pt imgsz=32 format=torchscript
- - name: Test segmentation
+ yolo segment train data=coco8-seg.yaml model=yolov8n-seg.yaml epochs=1 imgsz=32
+ yolo segment train data=coco8-seg.yaml model=yolov8n-seg.pt epochs=1 imgsz=32
+ yolo segment val data=coco8-seg.yaml model=runs/segment/train/weights/last.pt imgsz=32
+ yolo segment predict model=runs/segment/train/weights/last.pt imgsz=32 source=ultralytics/assets/bus.jpg
+ yolo export model=runs/segment/train/weights/last.pt imgsz=32 format=torchscript
+ - name: Test Classify
shell: bash # for Windows compatibility
run: |
- yolo task=segment mode=train data=coco8-seg.yaml model=yolov8n-seg.yaml epochs=1 imgsz=32
- yolo task=segment mode=train data=coco8-seg.yaml model=yolov8n-seg.pt epochs=1 imgsz=32
- yolo task=segment mode=val data=coco8-seg.yaml model=runs/segment/train/weights/last.pt imgsz=32
- yolo task=segment mode=predict model=runs/segment/train/weights/last.pt imgsz=32 source=ultralytics/assets/bus.jpg
- yolo mode=export model=runs/segment/train/weights/last.pt imgsz=32 format=torchscript
- - name: Test classification
+ yolo classify train data=imagenet10 model=yolov8n-cls.yaml epochs=1 imgsz=32
+ yolo classify train data=imagenet10 model=yolov8n-cls.pt epochs=1 imgsz=32
+ yolo classify val data=imagenet10 model=runs/classify/train/weights/last.pt imgsz=32
+ yolo classify predict model=runs/classify/train/weights/last.pt imgsz=32 source=ultralytics/assets/bus.jpg
+ yolo export model=runs/classify/train/weights/last.pt imgsz=32 format=torchscript
+ - name: Test Pose
shell: bash # for Windows compatibility
run: |
- yolo task=classify mode=train data=imagenet10 model=yolov8n-cls.yaml epochs=1 imgsz=32
- yolo task=classify mode=train data=imagenet10 model=yolov8n-cls.pt epochs=1 imgsz=32
- yolo task=classify mode=val data=imagenet10 model=runs/classify/train/weights/last.pt imgsz=32
- yolo task=classify mode=predict model=runs/classify/train/weights/last.pt imgsz=32 source=ultralytics/assets/bus.jpg
- yolo mode=export model=runs/classify/train/weights/last.pt imgsz=32 format=torchscript
+ yolo pose train data=coco8-pose.yaml model=yolov8n-pose.yaml epochs=1 imgsz=32
+ yolo pose train data=coco8-pose.yaml model=yolov8n-pose.pt epochs=1 imgsz=32
+ yolo pose val data=coco8-pose.yaml model=runs/pose/train/weights/last.pt imgsz=32
+ yolo pose predict model=runs/pose/train/weights/last.pt imgsz=32 source=ultralytics/assets/bus.jpg
+ yolo export model=runs/pose/train/weights/last.pt imgsz=32 format=torchscript
- name: Pytest tests
shell: bash # for Windows compatibility
run: pytest tests
diff --git a/README.md b/README.md
index c1683e4..f922504 100644
--- a/README.md
+++ b/README.md
@@ -109,7 +109,10 @@ YOLOv8 [Python Docs](https://docs.ultralytics.com/usage/python) for more example
## Models
-All YOLOv8 pretrained models are available here. Detect, Segment and Pose models are pretrained on the [COCO](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/datasets/coco.yaml) dataset, while Classify models are pretrained on the [ImageNet](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/datasets/ImageNet.yaml) dataset.
+All YOLOv8 pretrained models are available here. Detect, Segment and Pose models are pretrained on
+the [COCO](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/datasets/coco.yaml) dataset, while Classify
+models are pretrained on
+the [ImageNet](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/datasets/ImageNet.yaml) dataset.
[Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models) download automatically from the latest
Ultralytics [release](https://github.com/ultralytics/assets/releases) on first use.
@@ -174,6 +177,28 @@ See [Classification Docs](https://docs.ultralytics.com/tasks/classify/) for usag
+Pose
+
+See [Pose Docs](https://docs.ultralytics.com/tasks/) for usage examples with these models.
+
+| Model | size
(pixels) | mAPbox
50-95 | mAPpose
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) |
+| ---------------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
+| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | - | 49.7 | - | - | 3.3 | 9.2 |
+| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | - | 59.2 | - | - | 11.6 | 30.2 |
+| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | - | 63.6 | - | - | 26.4 | 81.0 |
+| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | - | 67.0 | - | - | 44.4 | 168.6 |
+| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | - | 68.9 | - | - | 69.4 | 263.2 |
+| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | - | 71.5 | - | - | 99.1 | 1066.4 |
+
+- **mAPval** values are for single-model single-scale on [COCO Keypoints val2017](http://cocodataset.org)
+ dataset.
+
Reproduce by `yolo val pose data=coco-pose.yaml device=0`
+- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/)
+ instance.
+
Reproduce by `yolo val pose data=coco8-pose.yaml batch=1 device=0|cpu`
+
+Integrations
diff --git a/README.zh-CN.md b/README.zh-CN.md
index 81e568c..b709b3d 100644
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@ -163,6 +163,28 @@ Ultralytics [发布页](https://github.com/ultralytics/ultralytics/releases) 自
+Pose
+
+See [Pose Docs](https://docs.ultralytics.com/tasks/) for usage examples with these models.
+
+| Model | size
(pixels) | mAPbox
50-95 | mAPpose
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) |
+| ---------------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
+| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | - | 49.7 | - | - | 3.3 | 9.2 |
+| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | - | 59.2 | - | - | 11.6 | 30.2 |
+| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | - | 63.6 | - | - | 26.4 | 81.0 |
+| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | - | 67.0 | - | - | 44.4 | 168.6 |
+| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | - | 68.9 | - | - | 69.4 | 263.2 |
+| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | - | 71.5 | - | - | 99.1 | 1066.4 |
+
+- **mAPval** values are for single-model single-scale on [COCO Keypoints val2017](http://cocodataset.org)
+ dataset.
+
Reproduce by `yolo val pose data=coco-pose.yaml device=0`
+- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/)
+ instance.
+
Reproduce by `yolo val pose data=coco8-pose.yaml batch=1 device=0|cpu`
+
+模块集成
diff --git a/docker/Dockerfile b/docker/Dockerfile
index f9d0c4c..22cd80b 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -2,7 +2,7 @@
# Builds ultralytics/ultralytics:latest image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics
# Image is CUDA-optimized for YOLOv8 single/multi-GPU training and inference
-# Start FROM PyTorch image https://hub.docker.com/r/pytorch/pytorch
+# Start FROM PyTorch image https://hub.docker.com/r/pytorch/pytorch or nvcr.io/nvidia/pytorch:23.03-py3
FROM pytorch/pytorch:2.0.0-cuda11.7-cudnn8-runtime
# Downloads to user config dir
diff --git a/docs/index.md b/docs/index.md
index e054ee1..ec61e49 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -42,4 +42,4 @@ Since its launch YOLO has been employed in various applications, including auton
YOLOv8 is designed with a strong focus on speed, size, and accuracy, making it a compelling choice for various vision AI tasks. It outperforms previous versions by incorporating innovations like a new backbone network, a new anchor-free split head, and new loss functions. These improvements enable YOLOv8 to deliver superior results, while maintaining a compact size and exceptional speed.
-Additionally, YOLOv8 supports a full range of vision AI tasks, including [detection](tasks/detect.md), [segmentation](tasks/segment.md), [pose estimation](tasks/keypoints.md), [tracking](modes/track.md), and [classification](tasks/classify.md). This versatility allows users to leverage YOLOv8's capabilities across diverse applications and domains.
+Additionally, YOLOv8 supports a full range of vision AI tasks, including [detection](tasks/detect.md), [segmentation](tasks/segment.md), [pose estimation](tasks/pose.md), [tracking](modes/track.md), and [classification](tasks/classify.md). This versatility allows users to leverage YOLOv8's capabilities across diverse applications and domains.
diff --git a/docs/modes/benchmark.md b/docs/modes/benchmark.md
index b57e093..662a013 100644
--- a/docs/modes/benchmark.md
+++ b/docs/modes/benchmark.md
@@ -1,7 +1,7 @@
**Benchmark mode** is used to profile the speed and accuracy of various export formats for YOLOv8. The benchmarks
-provide information on the size of the exported format, its `mAP50-95` metrics (for object detection and segmentation)
+provide information on the size of the exported format, its `mAP50-95` metrics (for object detection, segmentation and pose)
or `accuracy_top5` metrics (for classification), and the inference time in milliseconds per image across various export
formats like ONNX, OpenVINO, TensorRT and others. This information can help users choose the optimal export format for
their specific use case based on their requirements for speed and accuracy.
diff --git a/docs/modes/index.md b/docs/modes/index.md
index ffa544a..1ca2383 100644
--- a/docs/modes/index.md
+++ b/docs/modes/index.md
@@ -54,7 +54,7 @@ for applications such as surveillance systems or self-driving cars.
## [Benchmark](benchmark.md)
Benchmark mode is used to profile the speed and accuracy of various export formats for YOLOv8. The benchmarks provide
-information on the size of the exported format, its `mAP50-95` metrics (for object detection and segmentation)
+information on the size of the exported format, its `mAP50-95` metrics (for object detection, segmentation and pose)
or `accuracy_top5` metrics (for classification), and the inference time in milliseconds per image across various export
formats like ONNX, OpenVINO, TensorRT and others. This information can help users choose the optimal export format for
their specific use case based on their requirements for speed and accuracy.
diff --git a/docs/modes/train.md b/docs/modes/train.md
index e68c8b8..a9275a0 100644
--- a/docs/modes/train.md
+++ b/docs/modes/train.md
@@ -88,6 +88,8 @@ task.
| `box` | `7.5` | box loss gain |
| `cls` | `0.5` | cls loss gain (scale with pixels) |
| `dfl` | `1.5` | dfl loss gain |
+| `pose` | `12.0` | pose loss gain (pose-only) |
+| `kobj` | `2.0` | keypoint obj loss gain (pose-only) |
| `fl_gamma` | `0.0` | focal loss gamma (efficientDet default gamma=1.5) |
| `label_smoothing` | `0.0` | label smoothing (fraction) |
| `nbs` | `64` | nominal batch size |
diff --git a/docs/reference/ops.md b/docs/reference/ops.md
index 8c4f1b7..3f8246d 100644
--- a/docs/reference/ops.md
+++ b/docs/reference/ops.md
@@ -175,9 +175,9 @@ show_source: false
show_root_toc_entry: false
---
-## scale_segments
+## scale_coords
-:::ultralytics.yolo.utils.ops.scale_segments
+:::ultralytics.yolo.utils.ops.scale_coords
handler: python
options:
show_source: false
@@ -193,9 +193,9 @@ show_source: false
show_root_toc_entry: false
---
-## clip_segments
+## clip_coords
-:::ultralytics.yolo.utils.ops.clip_segments
+:::ultralytics.yolo.utils.ops.clip_coords
handler: python
options:
show_source: false
diff --git a/docs/tasks/classify.md b/docs/tasks/classify.md
index 3c8cb6f..d985d46 100644
--- a/docs/tasks/classify.md
+++ b/docs/tasks/classify.md
@@ -122,7 +122,7 @@ Use a trained YOLOv8n-cls model to run predictions on images.
yolo classify predict model=path/to/best.pt source='https://ultralytics.com/images/bus.jpg' # predict with custom model
```
-Read more details of `predict` in our [Predict](https://docs.ultralytics.com/modes/predict/) page.
+See full `predict` mode details in the [Predict](https://docs.ultralytics.com/modes/predict/) page.
## Export
@@ -150,7 +150,7 @@ Export a YOLOv8n-cls model to a different format like ONNX, CoreML, etc.
```
Available YOLOv8-cls export formats are in the table below. You can predict or validate directly on exported models,
-i.e. `yolo predict model=yolov8n-cls.onnx`.
+i.e. `yolo predict model=yolov8n-cls.onnx`. Usage examples are shown for your model after export completes.
| Format | `format` Argument | Model | Metadata |
|--------------------------------------------------------------------|-------------------|-------------------------------|----------|
@@ -167,3 +167,4 @@ i.e. `yolo predict model=yolov8n-cls.onnx`.
| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-cls_web_model/` | ✅ |
| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-cls_paddle_model/` | ✅ |
+See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page.
diff --git a/docs/tasks/detect.md b/docs/tasks/detect.md
index 34b580d..89cd1d2 100644
--- a/docs/tasks/detect.md
+++ b/docs/tasks/detect.md
@@ -123,7 +123,7 @@ Use a trained YOLOv8n model to run predictions on images.
yolo detect predict model=path/to/best.pt source='https://ultralytics.com/images/bus.jpg' # predict with custom model
```
-Read more details of `predict` in our [Predict](https://docs.ultralytics.com/modes/predict/) page.
+See full `predict` mode details in the [Predict](https://docs.ultralytics.com/modes/predict/) page.
## Export
@@ -151,7 +151,7 @@ Export a YOLOv8n model to a different format like ONNX, CoreML, etc.
```
Available YOLOv8 export formats are in the table below. You can predict or validate directly on exported models,
-i.e. `yolo predict model=yolov8n.onnx`.
+i.e. `yolo predict model=yolov8n.onnx`. Usage examples are shown for your model after export completes.
| Format | `format` Argument | Model | Metadata |
|--------------------------------------------------------------------|-------------------|---------------------------|----------|
@@ -167,3 +167,5 @@ i.e. `yolo predict model=yolov8n.onnx`.
| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ |
| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ |
| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ |
+
+See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page.
diff --git a/docs/tasks/index.md b/docs/tasks/index.md
index 3276d53..47bbd39 100644
--- a/docs/tasks/index.md
+++ b/docs/tasks/index.md
@@ -2,7 +2,7 @@
YOLOv8 is an AI framework that supports multiple computer vision **tasks**. The framework can be used to
perform [detection](detect.md), [segmentation](segment.md), [classification](classify.md),
-and [keypoints](keypoints.md) detection. Each of these tasks has a different objective and use case.
+and [pose](pose.md) estimation. Each of these tasks has a different objective and use case.
@@ -29,15 +29,13 @@ images based on their content. It uses a variant of the EfficientNet architectur
[Classification Examples](classify.md){ .md-button .md-button--primary}
-
+[Pose Examples](pose.md){ .md-button .md-button--primary}
## Conclusion
diff --git a/docs/tasks/keypoints.md b/docs/tasks/keypoints.md
deleted file mode 100644
index d9f2484..0000000
--- a/docs/tasks/keypoints.md
+++ /dev/null
@@ -1,149 +0,0 @@
-Key Point 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 keypoint detector is a set of points that represent the keypoints on the object in the image, usually
-along with the confidence scores for each point. Keypoint 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 _keypoints_ models use the `-kpts` suffix, i.e. `yolov8n-kpts.pt`. These models are trained on the COCO dataset and are suitable for a variety of keypoint estimation tasks.
-
-[Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/v8){ .md-button .md-button--primary}
-
-## Train TODO
-
-Train an OpenPose model on a custom dataset of keypoints using the OpenPose framework. For more information on how to
-train an OpenPose model on a custom dataset, see the OpenPose Training page.
-
-!!! example ""
-
- === "Python"
-
- ```python
- from ultralytics import YOLO
-
- # Load a model
- model = YOLO('yolov8n.yaml') # build a new model from YAML
- model = YOLO('yolov8n.pt') # load a pretrained model (recommended for training)
- model = YOLO('yolov8n.yaml').load('yolov8n.pt') # build from YAML and transfer weights
-
- # Train the model
- model.train(data='coco128.yaml', epochs=100, imgsz=640)
- ```
- === "CLI"
-
- ```bash
- # Build a new model from YAML and start training from scratch
- yolo detect train data=coco128.yaml model=yolov8n.yaml epochs=100 imgsz=640
-
- # Start training from a pretrained *.pt model
- yolo detect train data=coco128.yaml model=yolov8n.pt epochs=100 imgsz=640
-
- # Build a new model from YAML, transfer pretrained weights to it and start training
- yolo detect train data=coco128.yaml model=yolov8n.yaml pretrained=yolov8n.pt epochs=100 imgsz=640
- ```
-
-## Val TODO
-
-Validate trained YOLOv8n model accuracy on the COCO128 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.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 detect val model=yolov8n.pt # val official model
- yolo detect val model=path/to/best.pt # val custom model
- ```
-
-## Predict TODO
-
-Use a trained YOLOv8n model to run predictions on images.
-
-!!! example ""
-
- === "Python"
-
- ```python
- from ultralytics import YOLO
-
- # Load a model
- model = YOLO('yolov8n.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 detect predict model=yolov8n.pt source='https://ultralytics.com/images/bus.jpg' # predict with official model
- yolo detect predict model=path/to/best.pt source='https://ultralytics.com/images/bus.jpg' # predict with custom model
- ```
-
-Read more details of `predict` in our [Predict](https://docs.ultralytics.com/modes/predict/) page.
-
-## Export TODO
-
-Export a YOLOv8n model to a different format like ONNX, CoreML, etc.
-
-!!! example ""
-
- === "Python"
-
- ```python
- from ultralytics import YOLO
-
- # Load a model
- model = YOLO('yolov8n.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.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`.
-
-| Format | `format` Argument | Model | Metadata |
-|--------------------------------------------------------------------|-------------------|---------------------------|----------|
-| [PyTorch](https://pytorch.org/) | - | `yolov8n.pt` | ✅ |
-| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n.torchscript` | ✅ |
-| [ONNX](https://onnx.ai/) | `onnx` | `yolov8n.onnx` | ✅ |
-| [OpenVINO](https://docs.openvino.ai/latest/index.html) | `openvino` | `yolov8n_openvino_model/` | ✅ |
-| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n.engine` | ✅ |
-| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n.mlmodel` | ✅ |
-| [TF SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n_saved_model/` | ✅ |
-| [TF GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n.pb` | ❌ |
-| [TF Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n.tflite` | ✅ |
-| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ |
-| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ |
-| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ |
diff --git a/docs/tasks/pose.md b/docs/tasks/pose.md
new file mode 100644
index 0000000..e32bc7d
--- /dev/null
+++ b/docs/tasks/pose.md
@@ -0,0 +1,175 @@
+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](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/v8)
+
+YOLOv8 pretrained Pose models are shown here. Detect, Segment and Pose models are pretrained on
+the [COCO](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/datasets/coco.yaml) dataset, while Classify
+models are pretrained on
+the [ImageNet](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/datasets/ImageNet.yaml) dataset.
+
+[Models](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models) download automatically from the latest
+Ultralytics [release](https://github.com/ultralytics/assets/releases) on first use.
+
+| Model | size
(pixels) | mAPbox
50-95 | mAPpose
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) |
+|------------------------------------------------------------------------------------------------------|-----------------------|----------------------|-----------------------|--------------------------------|-------------------------------------|--------------------|-------------------|
+| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | - | 49.7 | - | - | 3.3 | 9.2 |
+| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | - | 59.2 | - | - | 11.6 | 30.2 |
+| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | - | 63.6 | - | - | 26.4 | 81.0 |
+| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | - | 67.0 | - | - | 44.4 | 168.6 |
+| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | - | 68.9 | - | - | 69.4 | 263.2 |
+| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | - | 71.5 | - | - | 99.1 | 1066.4 |
+
+- **mAPval** values are for single-model single-scale on [COCO Keypoints val2017](http://cocodataset.org)
+ dataset.
+
Reproduce by `yolo val pose data=coco-pose.yaml device=0`
+- **Speed** averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/)
+ 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='coco128-pose.yaml', epochs=100, imgsz=640)
+ ```
+ === "CLI"
+
+ ```bash
+ # Build a new model from YAML and start training from scratch
+ yolo detect train data=coco128-pose.yaml model=yolov8n-pose.yaml epochs=100 imgsz=640
+
+ # Start training from a pretrained *.pt model
+ yolo detect train data=coco128-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 detect train data=coco128-pose.yaml model=yolov8n-pose.yaml pretrained=yolov8n-pose.pt epochs=100 imgsz=640
+ ```
+
+## 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.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](https://docs.ultralytics.com/modes/predict/) page.
+
+## Export
+
+Export a YOLOv8n model to a different format like ONNX, CoreML, etc.
+
+!!! example ""
+
+ === "Python"
+
+ ```python
+ from ultralytics import YOLO
+
+ # Load a model
+ model = YOLO('yolov8n.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.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 |
+|--------------------------------------------------------------------|-------------------|--------------------------------|----------|
+| [PyTorch](https://pytorch.org/) | - | `yolov8n-pose.pt` | ✅ |
+| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n-pose.torchscript` | ✅ |
+| [ONNX](https://onnx.ai/) | `onnx` | `yolov8n-pose.onnx` | ✅ |
+| [OpenVINO](https://docs.openvino.ai/latest/index.html) | `openvino` | `yolov8n-pose_openvino_model/` | ✅ |
+| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n-pose.engine` | ✅ |
+| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n-pose.mlmodel` | ✅ |
+| [TF SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n-pose_saved_model/` | ✅ |
+| [TF GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n-pose.pb` | ❌ |
+| [TF Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n-pose.tflite` | ✅ |
+| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-pose_edgetpu.tflite` | ✅ |
+| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-pose_web_model/` | ✅ |
+| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-pose_paddle_model/` | ✅ |
+
+See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page.
diff --git a/docs/tasks/segment.md b/docs/tasks/segment.md
index 2ff7f58..67e4c6b 100644
--- a/docs/tasks/segment.md
+++ b/docs/tasks/segment.md
@@ -127,7 +127,7 @@ Use a trained YOLOv8n-seg model to run predictions on images.
yolo segment predict model=path/to/best.pt source='https://ultralytics.com/images/bus.jpg' # predict with custom model
```
-Read more details of `predict` in our [Predict](https://docs.ultralytics.com/modes/predict/) page.
+See full `predict` mode details in the [Predict](https://docs.ultralytics.com/modes/predict/) page.
## Export
@@ -155,7 +155,7 @@ Export a YOLOv8n-seg model to a different format like ONNX, CoreML, etc.
```
Available YOLOv8-seg export formats are in the table below. You can predict or validate directly on exported models,
-i.e. `yolo predict model=yolov8n-seg.onnx`.
+i.e. `yolo predict model=yolov8n-seg.onnx`. Usage examples are shown for your model after export completes.
| Format | `format` Argument | Model | Metadata |
|--------------------------------------------------------------------|-------------------|-------------------------------|----------|
@@ -172,4 +172,4 @@ i.e. `yolo predict model=yolov8n-seg.onnx`.
| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-seg_web_model/` | ✅ |
| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-seg_paddle_model/` | ✅ |
-
+See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page.
diff --git a/docs/usage/cfg.md b/docs/usage/cfg.md
index 0367ac4..c540f72 100644
--- a/docs/usage/cfg.md
+++ b/docs/usage/cfg.md
@@ -110,6 +110,8 @@ The training settings for YOLO models encompass various hyperparameters and conf
| `box` | `7.5` | box loss gain |
| `cls` | `0.5` | cls loss gain (scale with pixels) |
| `dfl` | `1.5` | dfl loss gain |
+| `pose` | `12.0` | pose loss gain (pose-only) |
+| `kobj` | `2.0` | keypoint obj loss gain (pose-only) |
| `fl_gamma` | `0.0` | focal loss gamma (efficientDet default gamma=1.5) |
| `label_smoothing` | `0.0` | label smoothing (fraction) |
| `nbs` | `64` | nominal batch size |
diff --git a/docs/usage/engine.md b/docs/usage/engine.md
index 5597be2..9cc85a1 100644
--- a/docs/usage/engine.md
+++ b/docs/usage/engine.md
@@ -74,7 +74,7 @@ trainer.add_callback("on_train_epoch_end", log_model) # Adds to existing callba
trainer.train()
```
-To know more about Callback triggering events and entry point, checkout our Callbacks guide # TODO
+To know more about Callback triggering events and entry point, checkout our [Callbacks Guide](callbacks.md)
## Other engine components
diff --git a/docs/usage/python.md b/docs/usage/python.md
index b5149ad..a4f6944 100644
--- a/docs/usage/python.md
+++ b/docs/usage/python.md
@@ -59,7 +59,6 @@ accurately predict the classes and locations of objects in an image.
=== "Resume"
```python
- # TODO: Resume feature is under development and should be released soon.
model = YOLO("last.pt")
model.train(resume=True)
```
diff --git a/examples/tutorial.ipynb b/examples/tutorial.ipynb
index 22f271b..deeb945 100644
--- a/examples/tutorial.ipynb
+++ b/examples/tutorial.ipynb
@@ -32,11 +32,11 @@
" ![\"Open](\"https://kaggle.com/static/images/open-in-kaggle.svg\")
\n",
"
\n",
"\n",
- "Welcome to the Ultralytics YOLOv8 🚀 notebook! YOLOv8 is the latest version of the YOLO (You Only Look Once) object detection and image segmentation model developed by Ultralytics. This notebook serves as the starting point for exploring the various resources available to help you get started with YOLOv8 and understand its features and capabilities.\n",
+ "Welcome to the Ultralytics YOLOv8 🚀 notebook! YOLOv8 is the latest version of the YOLO (You Only Look Once) AI models developed by Ultralytics. This notebook serves as the starting point for exploring the various resources available to help you get started with YOLOv8 and understand its features and capabilities.\n",
"\n",
- "The YOLOv8 models are designed to be fast, accurate, and easy to use, making them an excellent choice for a wide range of object detection and image segmentation tasks. They can be trained on large datasets and are capable of running on a variety of hardware platforms, from CPUs to GPUs.\n",
+ "YOLOv8 models are fast, accurate, and easy to use, making them ideal for various object detection and image segmentation tasks. They can be trained on large datasets and run on diverse hardware platforms, from CPUs to GPUs.\n",
"\n",
- "Whether you are a seasoned machine learning practitioner or new to the field, we hope that the resources in this notebook will help you get the most out of YOLOv8. Please feel free to browse the YOLOv8 Docs and reach out to us with any questions or feedback.\n",
+ "We hope that the resources in this notebook will help you get the most out of YOLOv8. Please browse the YOLOv8 Docs for details, raise an issue on GitHub for support, and join our Discord community for questions and discussions!\n",
"\n",
""
]
@@ -66,7 +66,7 @@
"import ultralytics\n",
"ultralytics.checks()"
],
- "execution_count": 1,
+ "execution_count": null,
"outputs": [
{
"output_type": "stream",
@@ -86,7 +86,7 @@
"source": [
"# 1. Predict\n",
"\n",
- "YOLOv8 may be used directly in the Command Line Interface (CLI) with a `yolo` command for a variety of tasks and modes and accepts additional arguments, i.e. `imgsz=640`. See a full list of available `yolo` [arguments](https://docs.ultralytics.com/usage/cfg/) in the YOLOv8 [Docs](https://docs.ultralytics.com).\n"
+ "YOLOv8 may be used directly in the Command Line Interface (CLI) with a `yolo` command for a variety of tasks and modes and accepts additional arguments, i.e. `imgsz=640`. See a full list of available `yolo` [arguments](https://docs.ultralytics.com/usage/cfg/) and other details in the [YOLOv8 Predict Docs](https://docs.ultralytics.com/modes/train/).\n"
]
},
{
@@ -102,7 +102,7 @@
"# Run inference on an image with YOLOv8n\n",
"!yolo predict model=yolov8n.pt source='https://ultralytics.com/images/zidane.jpg'"
],
- "execution_count": 3,
+ "execution_count": null,
"outputs": [
{
"output_type": "stream",
@@ -135,7 +135,7 @@
},
"source": [
"# 2. Val\n",
- "Validate a model's accuracy on the [COCO](https://cocodataset.org/#home) dataset's `val` or `test` splits. The latest YOLOv8 [models](https://github.com/ultralytics/ultralytics#models) are downloaded automatically the first time they are used."
+ "Validate a model's accuracy on the [COCO](https://cocodataset.org/#home) dataset's `val` or `test` splits. The latest YOLOv8 [models](https://github.com/ultralytics/ultralytics#models) are downloaded automatically the first time they are used. See [YOLOv8 Val Docs](https://docs.ultralytics.com/modes/val/) for more information."
]
},
{
@@ -165,7 +165,7 @@
"# Validate YOLOv8n on COCO128 val\n",
"!yolo val model=yolov8n.pt data=coco128.yaml"
],
- "execution_count": 4,
+ "execution_count": null,
"outputs": [
{
"output_type": "stream",
@@ -273,7 +273,7 @@
"\n",
"![](\"https://github.com/ultralytics/assets/raw/main/yolov8/banner-integrations.png\"/)
\n",
"\n",
- "Train YOLOv8 on [Detection](https://docs.ultralytics.com/tasks/detect/), [Segmentation](https://docs.ultralytics.com/tasks/segment/) and [Classification](https://docs.ultralytics.com/tasks/classify/) datasets."
+ "Train YOLOv8 on [Detect](https://docs.ultralytics.com/tasks/detect/), [Segment](https://docs.ultralytics.com/tasks/segment/), [Classify](https://docs.ultralytics.com/tasks/classify/) and [Pose](https://docs.ultralytics.com/tasks/pose/) datasets. See [YOLOv8 Train Docs](https://docs.ultralytics.com/modes/train/) for more information."
]
},
{
@@ -289,7 +289,7 @@
"# Train YOLOv8n on COCO128 for 3 epochs\n",
"!yolo train model=yolov8n.pt data=coco128.yaml epochs=3 imgsz=640"
],
- "execution_count": 5,
+ "execution_count": null,
"outputs": [
{
"output_type": "stream",
@@ -449,7 +449,7 @@
"source": [
"# 4. Export\n",
"\n",
- "Export a YOLOv8 model to any supported format with the `format` argument, i.e. `format=onnx`.\n",
+ "Export a YOLOv8 model to any supported format below with the `format` argument, i.e. `format=onnx`. See [YOLOv8 Export Docs](https://docs.ultralytics.com/modes/export/) for more information.\n",
"\n",
"- 💡 ProTip: Export to [ONNX](https://onnx.ai/) or [OpenVINO](https://docs.openvino.ai/latest/index.html) for up to 3x CPU speedup. \n",
"- 💡 ProTip: Export to [TensorRT](https://developer.nvidia.com/tensorrt) for up to 5x GPU speedup.\n",
@@ -487,7 +487,7 @@
"id": "CYIjW4igCjqD",
"outputId": "49b5bb9d-2c16-415b-c3e7-ec95c15a9e62"
},
- "execution_count": 6,
+ "execution_count": null,
"outputs": [
{
"output_type": "stream",
@@ -515,7 +515,7 @@
"source": [
"# 5. Python Usage\n",
"\n",
- "YOLOv8 was reimagined using Python-first principles for the most seamless Python YOLO experience yet. YOLOv8 models can be loaded from a trained checkpoint or created from scratch. Then methods are used to train, val, predict, and export the model. See a detailed Python usage examples in the YOLOv8 [Docs](https://docs.ultralytics.com/usage/python/)."
+ "YOLOv8 was reimagined using Python-first principles for the most seamless Python YOLO experience yet. YOLOv8 models can be loaded from a trained checkpoint or created from scratch. Then methods are used to train, val, predict, and export the model. See detailed Python usage examples in the [YOLOv8 Python Docs](https://docs.ultralytics.com/usage/python/)."
],
"metadata": {
"id": "kUMOQ0OeDBJG"
@@ -547,7 +547,7 @@
"source": [
"# 6. Tasks\n",
"\n",
- "YOLOv8 can train, val, predict and export models for the 3 primary tasks in vision AI: detection, segmentation and classification.\n",
+ "YOLOv8 can train, val, predict and export models for the most common tasks in vision AI: [Detect](https://docs.ultralytics.com/tasks/detect/), [Segment](https://docs.ultralytics.com/tasks/segment/), [Classify](https://docs.ultralytics.com/tasks/classify/) and [Pose](https://docs.ultralytics.com/tasks/pose/). See [YOLOv8 Tasks Docs](https://docs.ultralytics.com/tasks/) for more information.\n",
"\n",
"![](\"https://user-images.githubusercontent.com/26833433/212094133-6bb8c21c-3d47-41df-a512-81c5931054ae.png\")
\n"
],
@@ -636,6 +636,33 @@
"execution_count": null,
"outputs": []
},
+ {
+ "cell_type": "markdown",
+ "source": [
+ "## 4. Pose\n",
+ "\n",
+ "YOLOv8 _pose_ models use the `-pose` suffix, i.e. `yolov8n-pose.pt` and are pretrained on COCO Keypoints. See [Pose Docs](https://docs.ultralytics.com/tasks/pose/) for full details."
+ ],
+ "metadata": {
+ "id": "SpIaFLiO11TG"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# Load YOLOv8n-pose, train it on COCO8-pose for 3 epochs and predict an image with it\n",
+ "from ultralytics import YOLO\n",
+ "\n",
+ "model = YOLO('yolov8n-pose.pt') # load a pretrained YOLOv8n classification model\n",
+ "model.train(data='coco8-pose.yaml', epochs=3) # train the model\n",
+ "model('https://ultralytics.com/images/bus.jpg') # predict on an image"
+ ],
+ "metadata": {
+ "id": "si4aKFNg19vX"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
{
"cell_type": "markdown",
"metadata": {
diff --git a/mkdocs.yml b/mkdocs.yml
index 3ca07b3..85ade16 100644
--- a/mkdocs.yml
+++ b/mkdocs.yml
@@ -65,7 +65,7 @@ extra:
data: 0
note: >-
Thanks for your feedback!
- Tell us what we can improve.
+ Tell us what we can improve.
social:
- icon: fontawesome/brands/github
@@ -134,7 +134,7 @@ nav:
- Detect: tasks/detect.md
- Segment: tasks/segment.md
- Classify: tasks/classify.md
-# - Keypoints: tasks/keypoints.md
+ - Pose: tasks/pose.md
- Usage:
- CLI: usage/cli.md
- Python: usage/python.md
diff --git a/tests/test_cli.py b/tests/test_cli.py
index 3e5b8ce..2dca8a8 100644
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -33,6 +33,10 @@ def test_train_cls():
run(f'yolo train classify model={CFG}-cls.yaml data=imagenet10 imgsz=32 epochs=1')
+def test_train_pose():
+ run(f'yolo train pose model={CFG}-pose.yaml data=coco8-pose.yaml imgsz=32 epochs=1')
+
+
# Val checks -----------------------------------------------------------------------------------------------------------
def test_val_detect():
run(f'yolo val detect model={MODEL}.pt data=coco8.yaml imgsz=32')
@@ -46,6 +50,10 @@ def test_val_classify():
run(f'yolo val classify model={MODEL}-cls.pt data=imagenet10 imgsz=32')
+def test_val_pose():
+ run(f'yolo val pose model={MODEL}-pose.pt data=coco8-pose.yaml imgsz=32')
+
+
# Predict checks -------------------------------------------------------------------------------------------------------
def test_predict_detect():
run(f"yolo predict model={MODEL}.pt source={ROOT / 'assets'} imgsz=32 save save_crop save_txt")
@@ -63,6 +71,10 @@ def test_predict_classify():
run(f"yolo predict model={MODEL}-cls.pt source={ROOT / 'assets'} imgsz=32 save save_txt")
+def test_predict_pose():
+ run(f"yolo predict model={MODEL}-pose.pt source={ROOT / 'assets'} imgsz=32 save save_txt")
+
+
# Export checks --------------------------------------------------------------------------------------------------------
def test_export_detect_torchscript():
run(f'yolo export model={MODEL}.pt format=torchscript')
@@ -76,6 +88,10 @@ def test_export_classify_torchscript():
run(f'yolo export model={MODEL}-cls.pt format=torchscript')
+def test_export_classify_pose():
+ run(f'yolo export model={MODEL}-pose.pt format=torchscript')
+
+
def test_export_detect_edgetpu(enabled=False):
if enabled and LINUX:
run(f'yolo export model={MODEL}.pt format=edgetpu')
diff --git a/ultralytics/__init__.py b/ultralytics/__init__.py
index 1fb443f..496d5fd 100644
--- a/ultralytics/__init__.py
+++ b/ultralytics/__init__.py
@@ -1,6 +1,6 @@
# Ultralytics YOLO 🚀, GPL-3.0 license
-__version__ = '8.0.65'
+__version__ = '8.0.66'
from ultralytics.hub import start
from ultralytics.yolo.engine.model import YOLO
diff --git a/ultralytics/datasets/coco-pose.yaml b/ultralytics/datasets/coco-pose.yaml
new file mode 100644
index 0000000..537affd
--- /dev/null
+++ b/ultralytics/datasets/coco-pose.yaml
@@ -0,0 +1,38 @@
+# Ultralytics YOLO 🚀, GPL-3.0 license
+# COCO 2017 dataset http://cocodataset.org by Microsoft
+# Example usage: yolo train data=coco-pose.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+# └── coco-pose ← downloads here (20.1 GB)
+
+
+# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
+path: ../datasets/coco-pose # dataset root dir
+train: train2017.txt # train images (relative to 'path') 118287 images
+val: val2017.txt # val images (relative to 'path') 5000 images
+test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
+
+# Keypoints
+kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
+flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
+
+# Classes
+names:
+ 0: person
+
+# Download script/URL (optional)
+download: |
+ from ultralytics.yolo.utils.downloads import download
+ from pathlib import Path
+
+ # Download labels
+ dir = Path(yaml['path']) # dataset root dir
+ url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
+ urls = [url + 'coco2017labels-pose.zip'] # labels
+ download(urls, dir=dir.parent)
+ # Download data
+ urls = ['http://images.cocodataset.org/zips/train2017.zip', # 19G, 118k images
+ 'http://images.cocodataset.org/zips/val2017.zip', # 1G, 5k images
+ 'http://images.cocodataset.org/zips/test2017.zip'] # 7G, 41k images (optional)
+ download(urls, dir=dir / 'images', threads=3)
diff --git a/ultralytics/datasets/coco8-pose.yaml b/ultralytics/datasets/coco8-pose.yaml
new file mode 100644
index 0000000..367a4bb
--- /dev/null
+++ b/ultralytics/datasets/coco8-pose.yaml
@@ -0,0 +1,25 @@
+# Ultralytics YOLO 🚀, GPL-3.0 license
+# COCO8-pose dataset (first 8 images from COCO train2017) by Ultralytics
+# Example usage: yolo train data=coco8-pose.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+# └── coco8-pose ← downloads here (1 MB)
+
+
+# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
+path: ../datasets/coco8-pose # dataset root dir
+train: images/train # train images (relative to 'path') 4 images
+val: images/val # val images (relative to 'path') 4 images
+test: # test images (optional)
+
+# Keypoints
+kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
+flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
+
+# Classes
+names:
+ 0: person
+
+# Download script/URL (optional)
+download: https://ultralytics.com/assets/coco8-pose.zip
diff --git a/ultralytics/models/README.md b/ultralytics/models/README.md
index 7a291d9..e4d9da1 100644
--- a/ultralytics/models/README.md
+++ b/ultralytics/models/README.md
@@ -44,13 +44,14 @@ Any of these models can be used by loading their configs or pretrained checkpoin
### 1. YOLOv8
-**About** - Cutting edge Detection, Segmentation and Classification models developed by Ultralytics.
+**About** - Cutting edge Detection, Segmentation, Classification and Pose models developed by Ultralytics.
Available Models:
- Detection - `yolov8n`, `yolov8s`, `yolov8m`, `yolov8l`, `yolov8x`
- Instance Segmentation - `yolov8n-seg`, `yolov8s-seg`, `yolov8m-seg`, `yolov8l-seg`, `yolov8x-seg`
- Classification - `yolov8n-cls`, `yolov8s-cls`, `yolov8m-cls`, `yolov8l-cls`, `yolov8x-cls`
+- Pose - `yolov8n-pose`, `yolov8s-pose`, `yolov8m-pose`, `yolov8l-pose`, `yolov8x-pose`, `yolov8x-pose-p6`
Performance
@@ -84,6 +85,17 @@ Available Models:
| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 |
| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 |
+### Pose
+
+| Model | size
(pixels) | mAPbox
50-95 | mAPpose
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) |
+| ---------------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
+| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | - | 49.7 | - | - | 3.3 | 9.2 |
+| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | - | 59.2 | - | - | 11.6 | 30.2 |
+| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | - | 63.6 | - | - | 26.4 | 81.0 |
+| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | - | 67.0 | - | - | 44.4 | 168.6 |
+| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | - | 68.9 | - | - | 69.4 | 263.2 |
+| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | - | 71.5 | - | - | 99.1 | 1066.4 |
+