Instructions to use lewiswatson/yolov8x-tuned-hand-gestures with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use lewiswatson/yolov8x-tuned-hand-gestures with ultralytics:
from huggingface_hub import hf_hub_download from ultralytics import YOLO # pick the weights file from this repo's "Files and versions" tab weights = hf_hub_download("lewiswatson/yolov8x-tuned-hand-gestures", "<weights>.pt") model = YOLO(weights) source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
Yolov8x Tuned to Hand Gestures
Yolo v8x Finetuned on the hand gestures roboflow dataset.
Inference
from ultralyticsplus import YOLO, render_result
# load model
model = YOLO('lewiswatson/yolov8x-tuned-hand-gestures')
# set image
image = 'https://thumbs.dreamstime.com/b/young-man-showing-peace-sign-isolated-over-yellow-background-133210696.jpg'
# perform inference
results = model.predict(image)
# observe results
print(results[0].boxes)
render = render_result(model=model, image=image, result=results[0])
render.show()
Training Parameters
Trained using Ultralytics and Ultralyticsplus.
- Epochs: 10
- Optimiser: SGD
- Patience 50
- Imgsz: 640
- Batch: -1
- Downloads last month
- 88
Model tree for lewiswatson/yolov8x-tuned-hand-gestures
Base model
Ultralytics/YOLOv8