-
Notifications
You must be signed in to change notification settings - Fork 11
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
Is the implementation in caffe coming soon? #2
Comments
Hi, I have a script to generate stacked hourglass in caffe, do you need it? |
Yes, thank you. |
Hi Here is the script:https://drive.google.com/open?id=0BxORzoJl8N9PS0lHbFJHLWQ2RVJ1blRtYmI4b0ZpUVJMRWRZ. Place it under examples/rmpe/ and run the script from $RMPE_root Currently the input format is bbox format, I also implement the centerscale version as original stacked hourglass but not tested. You can modify the param in the script. However, the reason I do not public it now is that, it's hard to train using Caffe, always loss=nan, I only success in training it for 1 time and can not reproduce it. If you find the reason,please let me know. Hope this may help Best |
Hi, I use you script to generate the training prototxt, and I have some question when training.
|
Hi
|
Thanks.
|
As far as I can see, there is no problem with the network structure... Maybe you can try to init all the conv with xavier |
Thanks for reply. The hourglass prototxt of V2 can also obtain the right key point heatmap. |
Oh yes, the official BN layer is not that perfect:) |
Hi, Fang, |
Hi Anshan, Did you try the prototxt attached by lxltaibo in this issue and also change the BN version? |
Thank you for Fang. I will try @lxltaibo 's prototxt. |
Hi, Fang, |
@AnshanTJU For the caffe prototxt, that's a 2 stack version. You can try to extend it to the 8 stack version |
@AnshanTJU For torch, yes, it's for 8 stacked hourglass |
I try @lxltaibo 's prototxt.But I can't run successfully。Tip: The roi area of opencv is out of bounds |
Do you have the weights and solver for your model? I wish to try it but don't want to train from scratch |
@lxltaibo |
hi, we want to used the code in caffe, are you still working on caffe implementation? Is it coming soon?
The text was updated successfully, but these errors were encountered: