Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Inference visualize #2

Closed
apfjdld opened this issue Dec 16, 2021 · 3 comments
Closed

Inference visualize #2

apfjdld opened this issue Dec 16, 2021 · 3 comments

Comments

@apfjdld
Copy link

apfjdld commented Dec 16, 2021

Hi, I have some questions.

I used detector to visualize, and i got some coord.

It has {results, tot, load, pre, net, dec, post, merge}, and results has list, its length is 100.

Please let me know what meaning is the return value of detector.

If you have time, please give me some hint to make visualization.

Thank you for your implementations.

Best Regards.

@apfjdld apfjdld closed this as completed Dec 16, 2021
@apfjdld
Copy link
Author

apfjdld commented Dec 16, 2021

I found it thanks

@wolfworld6
Copy link

f you have time, please give me some hint to make visualization.

hello,have you done for the visualizition demo?

@apfjdld apfjdld reopened this Mar 17, 2022
@apfjdld apfjdld closed this as completed Mar 17, 2022
@apfjdld
Copy link
Author

apfjdld commented Mar 17, 2022

Yes, you have to define Detector first, and use the image as input.

img = cv2.imread(path)
pred = detector.run(img)
results = {}
results[0] = (pred['results'])
r = dataset.convert_eval_format_baseline(results)[0]
bbox = r['bbox']
score = r['score']
face_box = r['face_box']
face_kpts = r['face_kpts']
keypoints = r['keypoints']
lefthand_kpts = r['lefthand_kpts']
righthand_kpts = r['righthand_kpts']
foot_kpts = r['foot_kpts']

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants