forked from root-project/root
-
Notifications
You must be signed in to change notification settings - Fork 36
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
Pooling layer #10
Open
steremma
wants to merge
362
commits into
tmvadnn:master
Choose a base branch
from
steremma:pooling-layer
base: master
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Pooling layer #10
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ith clang: COMPILER="ccache clang" gets lost in CMake; using ccache does not work as there is no ccache-wrapper for clang-3.9. So just use clang-3.9 without ccache.
... not when echoing what is going to be run.
…he macro tutorials/gl/gviz3d.C (cocoa backend)
`"Return an array with the *lod* edge of all bins" -> "Return an array with the *low* edge of all bins"`
This reverts commit 8bb0a97. With ACLiC, which means if you do "root.exe hsimple.C+", ROOT generates library for hsimple.C and execute this library instead of interpreting it at runtime. This didn't work with our "preloading modules" infrastructure, as it's not even interpreting. We can fix this by 1. Adding NEEDED section when generating so files. This is like a "static linker" solution, which means we'll change rootcling_impl to properly add dependency libraries. 2. Try to get callback from library I think this makes ACLiC slower, so I like the 1st solution However, for now, let's just revert this patch.
- use auto - remove wrong #endif (prevent to execute le macro)
- spell check - formating
- spell check
- formatting
…t to R__SetZipMode().
…ate code duplication
…gle's units (rad, deg, grad). Fix; https://sft.its.cern.ch/jira/browse/ROOT-8476
…minate code duplication
…tectures. The tests include overlapping local views, as well as the case where depth > 0.
…xpect the same arguments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR enhances the Max Pooling Layer in the following ways:
Increased test coverage. Tests have been added for the backwards propagation, covering the cases where
depth > 1
, as well as overlapping receptive fields. The testing suite was also refactored using templates to eliminate code duplication.Bug Fix. The newly added tests exposed a bug in the
Reference
implementation of back-propagation, in the case of overlapping receptive fields. The bug is resolved.CUDA implementation. The GPU version is now fully functional in both forward and backward propagation.