-
Notifications
You must be signed in to change notification settings - Fork 204
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
Inquiry about the result with the uploaded pre-trained models #1
Comments
Hi Jaehyun, I've just looked into this and found there was a bug in the dataset creation script - sorry! I've just pushed an update to the code to fix this. Essentially there was a discrepancy between how scipy and opencv import image data. For my PoseNet work I used opencv, so I've changed the script to reflect this. You will need to:
Let me know how this works, you should be able to reproduce the figures in the ICCV paper. Alex |
Hi, @alexgkendall Thank you for your kind response! I re-converted lmdb data set as you commented, and it works really well :) For non-bayesian and single center crop inference, I got
For bayesian inference (I'm not sure the uploaded weights were trained in this fashion, but I just ran it for fun)
Once again, thank you for kind response! Jaehyun |
Awesome! |
Hi, this is Jaehyun Lim
First of all, thank you for sharing your work :)
I tried to run the posenets with the uploaded pretrained models by using the provided caffe version of yours.
However, the performance (median error) of the posenets with following settings and the pretrained models does not match with the reported performance in your paper.
I got
I further tried followings;
test_bayesian_posnet.py
and addingDROPOUT
layer at somewhereicp9
according to the providedtest_bayesian_posenet.prototxt
; however, it also provided almost the same results.I would appreciate if you give me some advises about possible mistakes that I might make.
Sincerely,
Jaehyun
The text was updated successfully, but these errors were encountered: