metadata

license: apache-2.0
tags:
  - object-detection
  - vision
  - YOLO
  - Pytorch
datasets:
  - COCO
metrics:
  - mAP

YOLOv8m model trained on COCO

YOLOv8m is the medium version of YOLOv8 model trained on COCO object detection (118k annotated images) at resolution 640x640. It was released in https://github.com/ultralytics/ultralytics.

We develop a modified version that could be supported by AMD Ryzen AI.

Model description

Ultralytics YOLOv8 is a cutting-edge, state-of-the-art (SOTA) model that builds upon the success of previous YOLO versions and introduces new features and improvements to further boost performance and flexibility. YOLOv8 is designed to be fast, accurate, and easy to use, making it an excellent choice for a wide range of object detection and tracking, instance segmentation, image classification and pose estimation tasks.

Intended uses & limitations

You can use the raw model for object detection. See the model hub to look for all available YOLOv8 models.

How to use

Installation

Follow Ryzen AI Installation to prepare the environment for Ryzen AI. Run the following script to install pre-requisites for this model.

pip install -r requirements.txt

Data Preparation (optional: for accuracy evaluation)

The dataset MSCOCO2017 contains 118287 images for training and 5000 images for validation.

Download COCO dataset and create directories like this:

└── datasets
     └── coco
           ├── annotations
           |   ├── instances_val2017.json
           |   └── ...
           ├── labels
           |   ├── val2017
           |   |   ├── 000000000139.txt
           |       ├── 000000000285.txt
           |       └── ...
           ├── images
           |   ├── val2017
           |   |   ├── 000000000139.jpg
           |       ├── 000000000285.jpg
           └── val2017.txt

put the val2017 image folder under images directory or use a softlink
the labels folder and val2017.txt above are generate by general_json2yolo.py, you need put these file in to the datasets/coco folder
modify the coco.yaml like this:

path: /path/to/your/datasets/coco  # dataset root dir
train: train2017.txt  # train images (relative to 'path') 118287 images
val: val2017.txt  # val images (relative to 'path') 5000 images

Test & Evaluation

Code snippet from onnx_inference.py on how to use

args = make_parser().parse_args()
source = args.image_path 
dataset = LoadImages(
    source, imgsz=imgsz, stride=32, auto=False, transforms=None, vid_stride=1
)
onnx_weight = args.model
onnx_model = onnxruntime.InferenceSession(onnx_weight)
for batch in dataset:
    path, im, im0s, vid_cap, s = batch
    im = preprocess(im)
    if len(im.shape) == 3:
        im = im[None]
    outputs = onnx_model.run(None, {onnx_model.get_inputs()[0].name: im.cpu().numpy()})
    outputs = [torch.tensor(item) for item in outputs]
    preds = post_process(outputs)
    preds = non_max_suppression(
        preds, 0.25, 0.7, agnostic=False, max_det=300, classes=None
    )
    plot_images(
        im,
        *output_to_target(preds, max_det=15),
        source,
        fname=args.output_path,
        names=names,
    )

Run inference for a single image

python onnx_inference.py -m ./yolov8m_qat.onnx -i /Path/To/Your/Image --ipu --provider_config /Path/To/Your/Provider_config

Note: vaip_config.json is located at the setup package of Ryzen AI (refer to Installation)

Test accuracy of the quantized model

python onnx_eval.py -m ./yolov8m_qat.onnx --ipu --provider_config /Path/To/Your/Provider_config

Performance

Metric	Quantized onnx
AP0.50:0.95	48.4

@software{yolov8_ultralytics,
  author = {Glenn Jocher and Ayush Chaurasia and Jing Qiu},
  title = {Ultralytics YOLOv8},
  version = {8.0.0},
  year = {2023},
  url = {https://github.com/ultralytics/ultralytics},
  orcid = {0000-0001-5950-6979, 0000-0002-7603-6750, 0000-0003-3783-7069},
  license = {AGPL-3.0}
}