`ultralytics 8.0.65` YOLOv8 Pose models (#1347)
Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Mert Can Demir <validatedev@gmail.com> Co-authored-by: Laughing <61612323+Laughing-q@users.noreply.github.com> Co-authored-by: Fabian Greavu <fabiangreavu@gmail.com> Co-authored-by: Yonghye Kwon <developer.0hye@gmail.com> Co-authored-by: Eric Pedley <ericpedley@gmail.com> Co-authored-by: JustasBart <40023722+JustasBart@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Aarni Koskela <akx@iki.fi> Co-authored-by: Sergio Sanchez <sergio.ssm.97@gmail.com> Co-authored-by: Bogdan Gheorghe <112427971+bogdan-galileo@users.noreply.github.com> Co-authored-by: Jaap van de Loosdrecht <jaap@vdlmv.nl> Co-authored-by: Noobtoss <96134731+Noobtoss@users.noreply.github.com> Co-authored-by: nerdyespresso <106761627+nerdyespresso@users.noreply.github.com> Co-authored-by: Farid Inawan <frdteknikelektro@gmail.com> Co-authored-by: Laughing-q <1185102784@qq.com> Co-authored-by: Alexander Duda <Alexander.Duda@me.com> Co-authored-by: Mehran Ghandehari <mehran.maps@gmail.com> Co-authored-by: Snyk bot <snyk-bot@snyk.io> Co-authored-by: majid nasiri <majnasai@gmail.com>single_channel
Ayush Chaurasia
2 years ago
committed by
GitHub
parent
9af3e69b1a
commit
1cb92d7f42
@ -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.
|
|
||||||
|
|
||||||
<img width="1024" src="https://user-images.githubusercontent.com/26833433/212094133-6bb8c21c-3d47-41df-a512-81c5931054ae.png">
|
|
||||||
|
|
||||||
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/` | ✅ |
|
|
||||||
@ -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.
|
||||||
|
|
||||||
|
<img width="1024" src="https://user-images.githubusercontent.com/26833433/212094133-6bb8c21c-3d47-41df-a512-81c5931054ae.png">
|
||||||
|
|
||||||
|
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<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>pose<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(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 |
|
||||||
|
|
||||||
|
- **mAP<sup>val</sup>** values are for single-model single-scale on [COCO Keypoints val2017](http://cocodataset.org)
|
||||||
|
dataset.
|
||||||
|
<br>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.
|
||||||
|
<br>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.
|
||||||
@ -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)
|
||||||
@ -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
|
||||||
@ -0,0 +1,57 @@
|
|||||||
|
# Ultralytics YOLO 🚀, GPL-3.0 license
|
||||||
|
# YOLOv8 object detection model with P3-P6 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
|
||||||
|
|
||||||
|
# Parameters
|
||||||
|
nc: 1 # number of classes
|
||||||
|
kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
|
||||||
|
scales: # model compound scaling constants, i.e. 'model=yolov8n-p6.yaml' will call yolov8-p6.yaml with scale 'n'
|
||||||
|
# [depth, width, max_channels]
|
||||||
|
n: [0.33, 0.25, 1024]
|
||||||
|
s: [0.33, 0.50, 1024]
|
||||||
|
m: [0.67, 0.75, 768]
|
||||||
|
l: [1.00, 1.00, 512]
|
||||||
|
x: [1.00, 1.25, 512]
|
||||||
|
|
||||||
|
# YOLOv8.0x6 backbone
|
||||||
|
backbone:
|
||||||
|
# [from, repeats, module, args]
|
||||||
|
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
|
||||||
|
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
|
||||||
|
- [-1, 3, C2f, [128, True]]
|
||||||
|
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
|
||||||
|
- [-1, 6, C2f, [256, True]]
|
||||||
|
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
|
||||||
|
- [-1, 6, C2f, [512, True]]
|
||||||
|
- [-1, 1, Conv, [768, 3, 2]] # 7-P5/32
|
||||||
|
- [-1, 3, C2f, [768, True]]
|
||||||
|
- [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64
|
||||||
|
- [-1, 3, C2f, [1024, True]]
|
||||||
|
- [-1, 1, SPPF, [1024, 5]] # 11
|
||||||
|
|
||||||
|
# YOLOv8.0x6 head
|
||||||
|
head:
|
||||||
|
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||||
|
- [[-1, 8], 1, Concat, [1]] # cat backbone P5
|
||||||
|
- [-1, 3, C2, [768, False]] # 14
|
||||||
|
|
||||||
|
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||||
|
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
|
||||||
|
- [-1, 3, C2, [512, False]] # 17
|
||||||
|
|
||||||
|
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||||
|
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
|
||||||
|
- [-1, 3, C2, [256, False]] # 20 (P3/8-small)
|
||||||
|
|
||||||
|
- [-1, 1, Conv, [256, 3, 2]]
|
||||||
|
- [[-1, 17], 1, Concat, [1]] # cat head P4
|
||||||
|
- [-1, 3, C2, [512, False]] # 23 (P4/16-medium)
|
||||||
|
|
||||||
|
- [-1, 1, Conv, [512, 3, 2]]
|
||||||
|
- [[-1, 14], 1, Concat, [1]] # cat head P5
|
||||||
|
- [-1, 3, C2, [768, False]] # 26 (P5/32-large)
|
||||||
|
|
||||||
|
- [-1, 1, Conv, [768, 3, 2]]
|
||||||
|
- [[-1, 11], 1, Concat, [1]] # cat head P6
|
||||||
|
- [-1, 3, C2, [1024, False]] # 29 (P6/64-xlarge)
|
||||||
|
|
||||||
|
- [[20, 23, 26, 29], 1, Pose, [nc, kpt_shape]] # Pose(P3, P4, P5, P6)
|
||||||
@ -0,0 +1,47 @@
|
|||||||
|
# Ultralytics YOLO 🚀, GPL-3.0 license
|
||||||
|
# YOLOv8-pose keypoints/pose estimation model. For Usage examples see https://docs.ultralytics.com/tasks/pose
|
||||||
|
|
||||||
|
# Parameters
|
||||||
|
nc: 1 # number of classes
|
||||||
|
kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
|
||||||
|
scales: # model compound scaling constants, i.e. 'model=yolov8n-pose.yaml' will call yolov8-pose.yaml with scale 'n'
|
||||||
|
# [depth, width, max_channels]
|
||||||
|
n: [0.33, 0.25, 1024]
|
||||||
|
s: [0.33, 0.50, 1024]
|
||||||
|
m: [0.67, 0.75, 768]
|
||||||
|
l: [1.00, 1.00, 512]
|
||||||
|
x: [1.00, 1.25, 512]
|
||||||
|
|
||||||
|
# YOLOv8.0n backbone
|
||||||
|
backbone:
|
||||||
|
# [from, repeats, module, args]
|
||||||
|
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
|
||||||
|
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
|
||||||
|
- [-1, 3, C2f, [128, True]]
|
||||||
|
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
|
||||||
|
- [-1, 6, C2f, [256, True]]
|
||||||
|
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
|
||||||
|
- [-1, 6, C2f, [512, True]]
|
||||||
|
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
|
||||||
|
- [-1, 3, C2f, [1024, True]]
|
||||||
|
- [-1, 1, SPPF, [1024, 5]] # 9
|
||||||
|
|
||||||
|
# YOLOv8.0n head
|
||||||
|
head:
|
||||||
|
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||||
|
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
|
||||||
|
- [-1, 3, C2f, [512]] # 12
|
||||||
|
|
||||||
|
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
|
||||||
|
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
|
||||||
|
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
|
||||||
|
|
||||||
|
- [-1, 1, Conv, [256, 3, 2]]
|
||||||
|
- [[-1, 12], 1, Concat, [1]] # cat head P4
|
||||||
|
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
|
||||||
|
|
||||||
|
- [-1, 1, Conv, [512, 3, 2]]
|
||||||
|
- [[-1, 9], 1, Concat, [1]] # cat head P5
|
||||||
|
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
|
||||||
|
|
||||||
|
- [[15, 18, 21], 1, Pose, [nc, kpt_shape]] # Pose(P3, P4, P5)
|
||||||
@ -1,5 +1,5 @@
|
|||||||
# Ultralytics YOLO 🚀, GPL-3.0 license
|
# Ultralytics YOLO 🚀, GPL-3.0 license
|
||||||
|
|
||||||
from ultralytics.yolo.v8 import classify, detect, segment
|
from ultralytics.yolo.v8 import classify, detect, pose, segment
|
||||||
|
|
||||||
__all__ = 'classify', 'segment', 'detect'
|
__all__ = 'classify', 'segment', 'detect', 'pose'
|
||||||
|
|||||||
@ -0,0 +1,7 @@
|
|||||||
|
# Ultralytics YOLO 🚀, GPL-3.0 license
|
||||||
|
|
||||||
|
from .predict import PosePredictor, predict
|
||||||
|
from .train import PoseTrainer, train
|
||||||
|
from .val import PoseValidator, val
|
||||||
|
|
||||||
|
__all__ = 'PoseTrainer', 'train', 'PoseValidator', 'val', 'PosePredictor', 'predict'
|
||||||
@ -0,0 +1,103 @@
|
|||||||
|
# Ultralytics YOLO 🚀, GPL-3.0 license
|
||||||
|
|
||||||
|
from ultralytics.yolo.engine.results import Results
|
||||||
|
from ultralytics.yolo.utils import DEFAULT_CFG, ROOT, ops
|
||||||
|
from ultralytics.yolo.utils.plotting import colors, save_one_box
|
||||||
|
from ultralytics.yolo.v8.detect.predict import DetectionPredictor
|
||||||
|
|
||||||
|
|
||||||
|
class PosePredictor(DetectionPredictor):
|
||||||
|
|
||||||
|
def postprocess(self, preds, img, orig_img):
|
||||||
|
preds = ops.non_max_suppression(preds,
|
||||||
|
self.args.conf,
|
||||||
|
self.args.iou,
|
||||||
|
agnostic=self.args.agnostic_nms,
|
||||||
|
max_det=self.args.max_det,
|
||||||
|
classes=self.args.classes,
|
||||||
|
nc=len(self.model.names))
|
||||||
|
|
||||||
|
results = []
|
||||||
|
for i, pred in enumerate(preds):
|
||||||
|
orig_img = orig_img[i] if isinstance(orig_img, list) else orig_img
|
||||||
|
shape = orig_img.shape
|
||||||
|
pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], shape).round()
|
||||||
|
pred_kpts = pred[:, 6:].view(len(pred), *self.model.kpt_shape) if len(pred) else pred[:, 6:]
|
||||||
|
pred_kpts = ops.scale_coords(img.shape[2:], pred_kpts, shape)
|
||||||
|
path, _, _, _, _ = self.batch
|
||||||
|
img_path = path[i] if isinstance(path, list) else path
|
||||||
|
results.append(
|
||||||
|
Results(orig_img=orig_img,
|
||||||
|
path=img_path,
|
||||||
|
names=self.model.names,
|
||||||
|
boxes=pred[:, :6],
|
||||||
|
keypoints=pred_kpts))
|
||||||
|
return results
|
||||||
|
|
||||||
|
def write_results(self, idx, results, batch):
|
||||||
|
p, im, im0 = batch
|
||||||
|
log_string = ''
|
||||||
|
if len(im.shape) == 3:
|
||||||
|
im = im[None] # expand for batch dim
|
||||||
|
self.seen += 1
|
||||||
|
imc = im0.copy() if self.args.save_crop else im0
|
||||||
|
if self.source_type.webcam or self.source_type.from_img: # batch_size >= 1
|
||||||
|
log_string += f'{idx}: '
|
||||||
|
frame = self.dataset.count
|
||||||
|
else:
|
||||||
|
frame = getattr(self.dataset, 'frame', 0)
|
||||||
|
self.data_path = p
|
||||||
|
self.txt_path = str(self.save_dir / 'labels' / p.stem) + ('' if self.dataset.mode == 'image' else f'_{frame}')
|
||||||
|
log_string += '%gx%g ' % im.shape[2:] # print string
|
||||||
|
self.annotator = self.get_annotator(im0)
|
||||||
|
|
||||||
|
det = results[idx].boxes # TODO: make boxes inherit from tensors
|
||||||
|
if len(det) == 0:
|
||||||
|
return f'{log_string}(no detections), '
|
||||||
|
for c in det.cls.unique():
|
||||||
|
n = (det.cls == c).sum() # detections per class
|
||||||
|
log_string += f"{n} {self.model.names[int(c)]}{'s' * (n > 1)}, "
|
||||||
|
|
||||||
|
kpts = reversed(results[idx].keypoints)
|
||||||
|
for k in kpts:
|
||||||
|
self.annotator.kpts(k, shape=results[idx].orig_shape)
|
||||||
|
|
||||||
|
# write
|
||||||
|
for j, d in enumerate(reversed(det)):
|
||||||
|
c, conf, id = int(d.cls), float(d.conf), None if d.id is None else int(d.id.item())
|
||||||
|
if self.args.save_txt: # Write to file
|
||||||
|
kpt = (kpts[j][:, :2] / d.orig_shape[[1, 0]]).reshape(-1).tolist()
|
||||||
|
box = d.xywhn.view(-1).tolist()
|
||||||
|
line = (c, *box, *kpt) + (conf, ) * self.args.save_conf + (() if id is None else (id, ))
|
||||||
|
with open(f'{self.txt_path}.txt', 'a') as f:
|
||||||
|
f.write(('%g ' * len(line)).rstrip() % line + '\n')
|
||||||
|
if self.args.save or self.args.show: # Add bbox to image
|
||||||
|
name = ('' if id is None else f'id:{id} ') + self.model.names[c]
|
||||||
|
label = (f'{name} {conf:.2f}' if self.args.show_conf else name) if self.args.show_labels else None
|
||||||
|
if self.args.boxes:
|
||||||
|
self.annotator.box_label(d.xyxy.squeeze(), label, color=colors(c, True))
|
||||||
|
if self.args.save_crop:
|
||||||
|
save_one_box(d.xyxy,
|
||||||
|
imc,
|
||||||
|
file=self.save_dir / 'crops' / self.model.model.names[c] / f'{self.data_path.stem}.jpg',
|
||||||
|
BGR=True)
|
||||||
|
|
||||||
|
return log_string
|
||||||
|
|
||||||
|
|
||||||
|
def predict(cfg=DEFAULT_CFG, use_python=False):
|
||||||
|
model = cfg.model or 'yolov8n-pose.pt'
|
||||||
|
source = cfg.source if cfg.source is not None else ROOT / 'assets' if (ROOT / 'assets').exists() \
|
||||||
|
else 'https://ultralytics.com/images/bus.jpg'
|
||||||
|
|
||||||
|
args = dict(model=model, source=source)
|
||||||
|
if use_python:
|
||||||
|
from ultralytics import YOLO
|
||||||
|
YOLO(model)(**args)
|
||||||
|
else:
|
||||||
|
predictor = PosePredictor(overrides=args)
|
||||||
|
predictor.predict_cli()
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
predict()
|
||||||
@ -0,0 +1,170 @@
|
|||||||
|
# Ultralytics YOLO 🚀, GPL-3.0 license
|
||||||
|
|
||||||
|
from copy import copy
|
||||||
|
|
||||||
|
import torch
|
||||||
|
import torch.nn as nn
|
||||||
|
|
||||||
|
from ultralytics.nn.tasks import PoseModel
|
||||||
|
from ultralytics.yolo import v8
|
||||||
|
from ultralytics.yolo.utils import DEFAULT_CFG
|
||||||
|
from ultralytics.yolo.utils.loss import KeypointLoss
|
||||||
|
from ultralytics.yolo.utils.metrics import OKS_SIGMA
|
||||||
|
from ultralytics.yolo.utils.ops import xyxy2xywh
|
||||||
|
from ultralytics.yolo.utils.plotting import plot_images, plot_results
|
||||||
|
from ultralytics.yolo.utils.tal import make_anchors
|
||||||
|
from ultralytics.yolo.utils.torch_utils import de_parallel
|
||||||
|
from ultralytics.yolo.v8.detect.train import Loss
|
||||||
|
|
||||||
|
|
||||||
|
# BaseTrainer python usage
|
||||||
|
class PoseTrainer(v8.detect.DetectionTrainer):
|
||||||
|
|
||||||
|
def __init__(self, cfg=DEFAULT_CFG, overrides=None):
|
||||||
|
if overrides is None:
|
||||||
|
overrides = {}
|
||||||
|
overrides['task'] = 'pose'
|
||||||
|
super().__init__(cfg, overrides)
|
||||||
|
|
||||||
|
def get_model(self, cfg=None, weights=None, verbose=True):
|
||||||
|
model = PoseModel(cfg, ch=3, nc=self.data['nc'], data_kpt_shape=self.data['kpt_shape'], verbose=verbose)
|
||||||
|
if weights:
|
||||||
|
model.load(weights)
|
||||||
|
|
||||||
|
return model
|
||||||
|
|
||||||
|
def set_model_attributes(self):
|
||||||
|
super().set_model_attributes()
|
||||||
|
self.model.kpt_shape = self.data['kpt_shape']
|
||||||
|
|
||||||
|
def get_validator(self):
|
||||||
|
self.loss_names = 'box_loss', 'pose_loss', 'kobj_loss', 'cls_loss', 'dfl_loss'
|
||||||
|
return v8.pose.PoseValidator(self.test_loader, save_dir=self.save_dir, args=copy(self.args))
|
||||||
|
|
||||||
|
def criterion(self, preds, batch):
|
||||||
|
if not hasattr(self, 'compute_loss'):
|
||||||
|
self.compute_loss = PoseLoss(de_parallel(self.model))
|
||||||
|
return self.compute_loss(preds, batch)
|
||||||
|
|
||||||
|
def plot_training_samples(self, batch, ni):
|
||||||
|
images = batch['img']
|
||||||
|
kpts = batch['keypoints']
|
||||||
|
cls = batch['cls'].squeeze(-1)
|
||||||
|
bboxes = batch['bboxes']
|
||||||
|
paths = batch['im_file']
|
||||||
|
batch_idx = batch['batch_idx']
|
||||||
|
plot_images(images,
|
||||||
|
batch_idx,
|
||||||
|
cls,
|
||||||
|
bboxes,
|
||||||
|
kpts=kpts,
|
||||||
|
paths=paths,
|
||||||
|
fname=self.save_dir / f'train_batch{ni}.jpg')
|
||||||
|
|
||||||
|
def plot_metrics(self):
|
||||||
|
plot_results(file=self.csv, pose=True) # save results.png
|
||||||
|
|
||||||
|
|
||||||
|
# Criterion class for computing training losses
|
||||||
|
class PoseLoss(Loss):
|
||||||
|
|
||||||
|
def __init__(self, model): # model must be de-paralleled
|
||||||
|
super().__init__(model)
|
||||||
|
self.kpt_shape = model.model[-1].kpt_shape
|
||||||
|
self.bce_pose = nn.BCEWithLogitsLoss()
|
||||||
|
is_pose = self.kpt_shape == [17, 3]
|
||||||
|
nkpt = self.kpt_shape[0] # number of keypoints
|
||||||
|
sigmas = torch.from_numpy(OKS_SIGMA).to(self.device) if is_pose else torch.ones(nkpt, device=self.device) / nkpt
|
||||||
|
self.keypoint_loss = KeypointLoss(sigmas=sigmas)
|
||||||
|
|
||||||
|
def __call__(self, preds, batch):
|
||||||
|
loss = torch.zeros(5, device=self.device) # box, cls, dfl, kpt_location, kpt_visibility
|
||||||
|
feats, pred_kpts = preds if isinstance(preds[0], list) else preds[1]
|
||||||
|
pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split(
|
||||||
|
(self.reg_max * 4, self.nc), 1)
|
||||||
|
|
||||||
|
# b, grids, ..
|
||||||
|
pred_scores = pred_scores.permute(0, 2, 1).contiguous()
|
||||||
|
pred_distri = pred_distri.permute(0, 2, 1).contiguous()
|
||||||
|
pred_kpts = pred_kpts.permute(0, 2, 1).contiguous()
|
||||||
|
|
||||||
|
dtype = pred_scores.dtype
|
||||||
|
imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0] # image size (h,w)
|
||||||
|
anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5)
|
||||||
|
|
||||||
|
# targets
|
||||||
|
batch_size = pred_scores.shape[0]
|
||||||
|
batch_idx = batch['batch_idx'].view(-1, 1)
|
||||||
|
targets = torch.cat((batch_idx, batch['cls'].view(-1, 1), batch['bboxes']), 1)
|
||||||
|
targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
|
||||||
|
gt_labels, gt_bboxes = targets.split((1, 4), 2) # cls, xyxy
|
||||||
|
mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)
|
||||||
|
|
||||||
|
# pboxes
|
||||||
|
pred_bboxes = self.bbox_decode(anchor_points, pred_distri) # xyxy, (b, h*w, 4)
|
||||||
|
pred_kpts = self.kpts_decode(anchor_points, pred_kpts.view(batch_size, -1, *self.kpt_shape)) # (b, h*w, 17, 3)
|
||||||
|
|
||||||
|
_, target_bboxes, target_scores, fg_mask, target_gt_idx = self.assigner(
|
||||||
|
pred_scores.detach().sigmoid(), (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype),
|
||||||
|
anchor_points * stride_tensor, gt_labels, gt_bboxes, mask_gt)
|
||||||
|
|
||||||
|
target_scores_sum = max(target_scores.sum(), 1)
|
||||||
|
|
||||||
|
# cls loss
|
||||||
|
# loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum # VFL way
|
||||||
|
loss[3] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum # BCE
|
||||||
|
|
||||||
|
# bbox loss
|
||||||
|
if fg_mask.sum():
|
||||||
|
target_bboxes /= stride_tensor
|
||||||
|
loss[0], loss[4] = self.bbox_loss(pred_distri, pred_bboxes, anchor_points, target_bboxes, target_scores,
|
||||||
|
target_scores_sum, fg_mask)
|
||||||
|
keypoints = batch['keypoints'].to(self.device).float().clone()
|
||||||
|
keypoints[..., 0] *= imgsz[1]
|
||||||
|
keypoints[..., 1] *= imgsz[0]
|
||||||
|
for i in range(batch_size):
|
||||||
|
if fg_mask[i].sum():
|
||||||
|
idx = target_gt_idx[i][fg_mask[i]]
|
||||||
|
gt_kpt = keypoints[batch_idx.view(-1) == i][idx] # (n, 51)
|
||||||
|
gt_kpt[..., 0] /= stride_tensor[fg_mask[i]]
|
||||||
|
gt_kpt[..., 1] /= stride_tensor[fg_mask[i]]
|
||||||
|
area = xyxy2xywh(target_bboxes[i][fg_mask[i]])[:, 2:].prod(1, keepdim=True)
|
||||||
|
pred_kpt = pred_kpts[i][fg_mask[i]]
|
||||||
|
kpt_mask = gt_kpt[..., 2] != 0
|
||||||
|
loss[1] += self.keypoint_loss(pred_kpt, gt_kpt, kpt_mask, area) # pose loss
|
||||||
|
# kpt_score loss
|
||||||
|
if pred_kpt.shape[-1] == 3:
|
||||||
|
loss[2] += self.bce_pose(pred_kpt[..., 2], kpt_mask.float()) # keypoint obj loss
|
||||||
|
|
||||||
|
loss[0] *= self.hyp.box # box gain
|
||||||
|
loss[1] *= self.hyp.pose / batch_size # pose gain
|
||||||
|
loss[2] *= self.hyp.kobj / batch_size # kobj gain
|
||||||
|
loss[3] *= self.hyp.cls # cls gain
|
||||||
|
loss[4] *= self.hyp.dfl # dfl gain
|
||||||
|
|
||||||
|
return loss.sum() * batch_size, loss.detach() # loss(box, cls, dfl)
|
||||||
|
|
||||||
|
def kpts_decode(self, anchor_points, pred_kpts):
|
||||||
|
y = pred_kpts.clone()
|
||||||
|
y[..., :2] *= 2.0
|
||||||
|
y[..., 0] += anchor_points[:, [0]] - 0.5
|
||||||
|
y[..., 1] += anchor_points[:, [1]] - 0.5
|
||||||
|
return y
|
||||||
|
|
||||||
|
|
||||||
|
def train(cfg=DEFAULT_CFG, use_python=False):
|
||||||
|
model = cfg.model or 'yolov8n-pose.yaml'
|
||||||
|
data = cfg.data or 'coco8-pose.yaml'
|
||||||
|
device = cfg.device if cfg.device is not None else ''
|
||||||
|
|
||||||
|
args = dict(model=model, data=data, device=device)
|
||||||
|
if use_python:
|
||||||
|
from ultralytics import YOLO
|
||||||
|
YOLO(model).train(**args)
|
||||||
|
else:
|
||||||
|
trainer = PoseTrainer(overrides=args)
|
||||||
|
trainer.train()
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
train()
|
||||||
@ -0,0 +1,213 @@
|
|||||||
|
# Ultralytics YOLO 🚀, GPL-3.0 license
|
||||||
|
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
import numpy as np
|
||||||
|
import torch
|
||||||
|
|
||||||
|
from ultralytics.yolo.utils import DEFAULT_CFG, LOGGER, ops
|
||||||
|
from ultralytics.yolo.utils.checks import check_requirements
|
||||||
|
from ultralytics.yolo.utils.metrics import OKS_SIGMA, PoseMetrics, box_iou, kpt_iou
|
||||||
|
from ultralytics.yolo.utils.plotting import output_to_target, plot_images
|
||||||
|
from ultralytics.yolo.v8.detect import DetectionValidator
|
||||||
|
|
||||||
|
|
||||||
|
class PoseValidator(DetectionValidator):
|
||||||
|
|
||||||
|
def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None):
|
||||||
|
super().__init__(dataloader, save_dir, pbar, args)
|
||||||
|
self.args.task = 'pose'
|
||||||
|
self.metrics = PoseMetrics(save_dir=self.save_dir)
|
||||||
|
|
||||||
|
def preprocess(self, batch):
|
||||||
|
batch = super().preprocess(batch)
|
||||||
|
batch['keypoints'] = batch['keypoints'].to(self.device).float()
|
||||||
|
return batch
|
||||||
|
|
||||||
|
def get_desc(self):
|
||||||
|
return ('%22s' + '%11s' * 10) % ('Class', 'Images', 'Instances', 'Box(P', 'R', 'mAP50', 'mAP50-95)', 'Pose(P',
|
||||||
|
'R', 'mAP50', 'mAP50-95)')
|
||||||
|
|
||||||
|
def postprocess(self, preds):
|
||||||
|
preds = ops.non_max_suppression(preds,
|
||||||
|
self.args.conf,
|
||||||
|
self.args.iou,
|
||||||
|
labels=self.lb,
|
||||||
|
multi_label=True,
|
||||||
|
agnostic=self.args.single_cls,
|
||||||
|
max_det=self.args.max_det,
|
||||||
|
nc=self.nc)
|
||||||
|
return preds
|
||||||
|
|
||||||
|
def init_metrics(self, model):
|
||||||
|
super().init_metrics(model)
|
||||||
|
self.kpt_shape = self.data['kpt_shape']
|
||||||
|
is_pose = self.kpt_shape == [17, 3]
|
||||||
|
nkpt = self.kpt_shape[0]
|
||||||
|
self.sigma = OKS_SIGMA if is_pose else np.ones(nkpt) / nkpt
|
||||||
|
|
||||||
|
def update_metrics(self, preds, batch):
|
||||||
|
# Metrics
|
||||||
|
for si, pred in enumerate(preds):
|
||||||
|
idx = batch['batch_idx'] == si
|
||||||
|
cls = batch['cls'][idx]
|
||||||
|
bbox = batch['bboxes'][idx]
|
||||||
|
kpts = batch['keypoints'][idx]
|
||||||
|
nl, npr = cls.shape[0], pred.shape[0] # number of labels, predictions
|
||||||
|
nk = kpts.shape[1] # number of keypoints
|
||||||
|
shape = batch['ori_shape'][si]
|
||||||
|
correct_kpts = torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device) # init
|
||||||
|
correct_bboxes = torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device) # init
|
||||||
|
self.seen += 1
|
||||||
|
|
||||||
|
if npr == 0:
|
||||||
|
if nl:
|
||||||
|
self.stats.append((correct_bboxes, correct_kpts, *torch.zeros(
|
||||||
|
(2, 0), device=self.device), cls.squeeze(-1)))
|
||||||
|
if self.args.plots:
|
||||||
|
self.confusion_matrix.process_batch(detections=None, labels=cls.squeeze(-1))
|
||||||
|
continue
|
||||||
|
|
||||||
|
# Predictions
|
||||||
|
if self.args.single_cls:
|
||||||
|
pred[:, 5] = 0
|
||||||
|
predn = pred.clone()
|
||||||
|
ops.scale_boxes(batch['img'][si].shape[1:], predn[:, :4], shape,
|
||||||
|
ratio_pad=batch['ratio_pad'][si]) # native-space pred
|
||||||
|
pred_kpts = predn[:, 6:].view(npr, nk, -1)
|
||||||
|
ops.scale_coords(batch['img'][si].shape[1:], pred_kpts, shape, ratio_pad=batch['ratio_pad'][si])
|
||||||
|
|
||||||
|
# Evaluate
|
||||||
|
if nl:
|
||||||
|
height, width = batch['img'].shape[2:]
|
||||||
|
tbox = ops.xywh2xyxy(bbox) * torch.tensor(
|
||||||
|
(width, height, width, height), device=self.device) # target boxes
|
||||||
|
ops.scale_boxes(batch['img'][si].shape[1:], tbox, shape,
|
||||||
|
ratio_pad=batch['ratio_pad'][si]) # native-space labels
|
||||||
|
tkpts = kpts.clone()
|
||||||
|
tkpts[..., 0] *= width
|
||||||
|
tkpts[..., 1] *= height
|
||||||
|
tkpts = ops.scale_coords(batch['img'][si].shape[1:], tkpts, shape, ratio_pad=batch['ratio_pad'][si])
|
||||||
|
labelsn = torch.cat((cls, tbox), 1) # native-space labels
|
||||||
|
correct_bboxes = self._process_batch(predn[:, :6], labelsn)
|
||||||
|
correct_kpts = self._process_batch(predn[:, :6], labelsn, pred_kpts, tkpts)
|
||||||
|
if self.args.plots:
|
||||||
|
self.confusion_matrix.process_batch(predn, labelsn)
|
||||||
|
|
||||||
|
# Append correct_masks, correct_boxes, pconf, pcls, tcls
|
||||||
|
self.stats.append((correct_bboxes, correct_kpts, pred[:, 4], pred[:, 5], cls.squeeze(-1)))
|
||||||
|
|
||||||
|
# Save
|
||||||
|
if self.args.save_json:
|
||||||
|
self.pred_to_json(predn, batch['im_file'][si])
|
||||||
|
# if self.args.save_txt:
|
||||||
|
# save_one_txt(predn, save_conf, shape, file=save_dir / 'labels' / f'{path.stem}.txt')
|
||||||
|
|
||||||
|
def _process_batch(self, detections, labels, pred_kpts=None, gt_kpts=None):
|
||||||
|
"""
|
||||||
|
Return correct prediction matrix
|
||||||
|
Arguments:
|
||||||
|
detections (array[N, 6]), x1, y1, x2, y2, conf, class
|
||||||
|
labels (array[M, 5]), class, x1, y1, x2, y2
|
||||||
|
pred_kpts (array[N, 51]), 51 = 17 * 3
|
||||||
|
gt_kpts (array[N, 51])
|
||||||
|
Returns:
|
||||||
|
correct (array[N, 10]), for 10 IoU levels
|
||||||
|
"""
|
||||||
|
if pred_kpts is not None and gt_kpts is not None:
|
||||||
|
# `0.53` is from https://github.com/jin-s13/xtcocoapi/blob/master/xtcocotools/cocoeval.py#L384
|
||||||
|
area = ops.xyxy2xywh(labels[:, 1:])[:, 2:].prod(1) * 0.53
|
||||||
|
iou = kpt_iou(gt_kpts, pred_kpts, sigma=self.sigma, area=area)
|
||||||
|
else: # boxes
|
||||||
|
iou = box_iou(labels[:, 1:], detections[:, :4])
|
||||||
|
|
||||||
|
correct = np.zeros((detections.shape[0], self.iouv.shape[0])).astype(bool)
|
||||||
|
correct_class = labels[:, 0:1] == detections[:, 5]
|
||||||
|
for i in range(len(self.iouv)):
|
||||||
|
x = torch.where((iou >= self.iouv[i]) & correct_class) # IoU > threshold and classes match
|
||||||
|
if x[0].shape[0]:
|
||||||
|
matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]),
|
||||||
|
1).cpu().numpy() # [label, detect, iou]
|
||||||
|
if x[0].shape[0] > 1:
|
||||||
|
matches = matches[matches[:, 2].argsort()[::-1]]
|
||||||
|
matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
|
||||||
|
# matches = matches[matches[:, 2].argsort()[::-1]]
|
||||||
|
matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
|
||||||
|
correct[matches[:, 1].astype(int), i] = True
|
||||||
|
return torch.tensor(correct, dtype=torch.bool, device=detections.device)
|
||||||
|
|
||||||
|
def plot_val_samples(self, batch, ni):
|
||||||
|
plot_images(batch['img'],
|
||||||
|
batch['batch_idx'],
|
||||||
|
batch['cls'].squeeze(-1),
|
||||||
|
batch['bboxes'],
|
||||||
|
kpts=batch['keypoints'],
|
||||||
|
paths=batch['im_file'],
|
||||||
|
fname=self.save_dir / f'val_batch{ni}_labels.jpg',
|
||||||
|
names=self.names)
|
||||||
|
|
||||||
|
def plot_predictions(self, batch, preds, ni):
|
||||||
|
pred_kpts = torch.cat([p[:, 6:].view(-1, *self.kpt_shape)[:15] for p in preds], 0)
|
||||||
|
plot_images(batch['img'],
|
||||||
|
*output_to_target(preds, max_det=15),
|
||||||
|
kpts=pred_kpts,
|
||||||
|
paths=batch['im_file'],
|
||||||
|
fname=self.save_dir / f'val_batch{ni}_pred.jpg',
|
||||||
|
names=self.names) # pred
|
||||||
|
|
||||||
|
def pred_to_json(self, predn, filename):
|
||||||
|
stem = Path(filename).stem
|
||||||
|
image_id = int(stem) if stem.isnumeric() else stem
|
||||||
|
box = ops.xyxy2xywh(predn[:, :4]) # xywh
|
||||||
|
box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner
|
||||||
|
for p, b in zip(predn.tolist(), box.tolist()):
|
||||||
|
self.jdict.append({
|
||||||
|
'image_id': image_id,
|
||||||
|
'category_id': self.class_map[int(p[5])],
|
||||||
|
'bbox': [round(x, 3) for x in b],
|
||||||
|
'keypoints': p[6:],
|
||||||
|
'score': round(p[4], 5)})
|
||||||
|
|
||||||
|
def eval_json(self, stats):
|
||||||
|
if self.args.save_json and self.is_coco and len(self.jdict):
|
||||||
|
anno_json = self.data['path'] / 'annotations/person_keypoints_val2017.json' # annotations
|
||||||
|
pred_json = self.save_dir / 'predictions.json' # predictions
|
||||||
|
LOGGER.info(f'\nEvaluating pycocotools mAP using {pred_json} and {anno_json}...')
|
||||||
|
try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
|
||||||
|
check_requirements('pycocotools>=2.0.6')
|
||||||
|
from pycocotools.coco import COCO # noqa
|
||||||
|
from pycocotools.cocoeval import COCOeval # noqa
|
||||||
|
|
||||||
|
for x in anno_json, pred_json:
|
||||||
|
assert x.is_file(), f'{x} file not found'
|
||||||
|
anno = COCO(str(anno_json)) # init annotations api
|
||||||
|
pred = anno.loadRes(str(pred_json)) # init predictions api (must pass string, not Path)
|
||||||
|
for i, eval in enumerate([COCOeval(anno, pred, 'bbox'), COCOeval(anno, pred, 'keypoints')]):
|
||||||
|
if self.is_coco:
|
||||||
|
eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files] # im to eval
|
||||||
|
eval.evaluate()
|
||||||
|
eval.accumulate()
|
||||||
|
eval.summarize()
|
||||||
|
idx = i * 4 + 2
|
||||||
|
stats[self.metrics.keys[idx + 1]], stats[
|
||||||
|
self.metrics.keys[idx]] = eval.stats[:2] # update mAP50-95 and mAP50
|
||||||
|
except Exception as e:
|
||||||
|
LOGGER.warning(f'pycocotools unable to run: {e}')
|
||||||
|
return stats
|
||||||
|
|
||||||
|
|
||||||
|
def val(cfg=DEFAULT_CFG, use_python=False):
|
||||||
|
model = cfg.model or 'yolov8n-pose.pt'
|
||||||
|
data = cfg.data or 'coco128-pose.yaml'
|
||||||
|
|
||||||
|
args = dict(model=model, data=data)
|
||||||
|
if use_python:
|
||||||
|
from ultralytics import YOLO
|
||||||
|
YOLO(model).val(**args)
|
||||||
|
else:
|
||||||
|
validator = PoseValidator(args=args)
|
||||||
|
validator(model=args['model'])
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
val()
|
||||||
Loading…
Reference in new issue