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

Demo results #6

Closed
dbaranchuk opened this issue Dec 6, 2016 · 4 comments
Closed

Demo results #6

dbaranchuk opened this issue Dec 6, 2016 · 4 comments

Comments

@dbaranchuk
Copy link

dbaranchuk commented Dec 6, 2016

Hi,

I've run your demo code and got pretty weird results:

method Head Knee Ankle Shoulder Elbow Wrist Hip
valid-example 96.52 78.60 73.52 93.51 85.18 79.17 84.14
valid-ours 96.67 83.10 79.07 94.68 88.54 83.38 87.49

I downloaded your pre-trained model and MPII dataset and followed the instructions. Could you explain please why results are much worse than in #1 ? Have you updated this model since that time ?

Thanks!

@anewell
Copy link
Collaborator

anewell commented Dec 9, 2016

Hm, that's interesting, I did update the model recently, but it is supposed to be a better version. Perhaps I made a mistake, and will look into it.

@sunke123
Copy link

Hi, the new model can achieve 87.9 on validation.
You just need to select which stage you want.
In this code, the default is stage 2. So, you obtain a worse result.
If you set it as 8, you can get the 87.9.
local hm = out[stage_num][1]:float()

@anewell
Copy link
Collaborator

anewell commented Feb 3, 2017

Thanks for pointing that out, I've updated the file with the fix

@anewell anewell closed this as completed Feb 3, 2017
@larklili
Copy link

larklili commented Apr 9, 2018

hi,could you please tell me how to solve with .h5 files?i have get full predictions of MPII

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

4 participants