-
Notifications
You must be signed in to change notification settings - Fork 18.6k
setting default power_wrapper batch size to match the imagenet_deploy pr... #34
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
Conversation
How about rebasing to only include aeca741? The rest are in-progress feat pyramid commits that aren't ready for master. Once you rebase you can You should make a |
Sure. Evan, can we do this together tomorrow? I'll be in 7SDH at 2-3pm tomorrow to discuss caffe feat-pyramids with Forrest On Wed, Jan 15, 2014 at 2:27 PM, Evan Shelhamer [email protected]:
Forrest Iandola |
I'm in New York at the moment, but I'm still happy to walk you through the pull request change.
p.s. Looks like a lot of coding progress on the feature pyramids! |
Evan, thanks a lot. after I do these commands...
tl;dr, after I do this stuff, where will I see my latest version? Forrest On Thu, Jan 16, 2014 at 7:51 AM, Evan Shelhamer [email protected]:
Forrest Iandola |
Forrest, master will be back to aeca741 git branch makes the branch without checking it out. you're reverting and Make sense? Happy to clear up more if needed. Le jeudi 16 janvier 2014, Forrest Iandola [email protected] a
|
Hi Evan, All right, the pull request should be ready to go. My featpyramid experimental code is now in my 'featpyramid' branch. Thanks for the help! Forrest On Thu, Jan 16, 2014 at 2:03 PM, Evan Shelhamer [email protected]:
Forrest Iandola |
set default power_wrapper batch size to match the imagenet_deploy compatible out-of-the-box with the ipython notebook tutorial
set default power_wrapper batch size to match the imagenet_deploy compatible out-of-the-box with the ipython notebook tutorial
Setting power_wrapper's batchsize to match imagenet_deploy prototxt. (so that power_wrapper works out of the box on the ipython notebook tutorial.)
[also, my first caffe pull request... making sure all the plumbing works.]