search

Deci-AI / super-gradients

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.
https://www.supergradients.com
Apache License 2.0
4.59k stars 509 forks source link

Work with keypoints for recognize some poses #2008

Open abduladolph23 opened 5 months ago

abduladolph23 commented 5 months ago

💡 Your Question

Hi, i want to recognize when a person is raising their hand. My idea is to calculate when the keypoint of the hand is greater than the keypoint of shoulder (something like that). But I'm not able to get the keypoints of the body. Please i really need help :( .

I'm using supergradients -> 3.7.1

And the way i'm doing the recognition is: ` import super_gradients import torch

from super_gradients.training import models from super_gradients.common.object_names import Models

device = 'cuda' if torch.cuda.is_available() else 'cpu'

model = models.get(Models.YOLO_NAS_POSE_N, pretrained_weights="coco_pose") model = model.to(device)

model.predict_webcam(conf=.75)

`

Versions

No response

guor8bu commented 4 months ago

Hi, Did you find the solution? I am trying to get them as well, at least the coordinate of all key points, don't need a specific one