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

Detection #13

Open
wants to merge 1,092 commits into
base: master
Choose a base branch
from
Open

Detection #13

wants to merge 1,092 commits into from

Conversation

NourElmadany
Copy link

No description provided.

yjxiong and others added 30 commits July 6, 2015 12:35
No functional changes, just fixing whitespace errors and typos in
comments
Add action recognition contents
Making the net_spec python3 compatible
List protobuf-compiler dependency in the correct place (it is in the …
Conflicts:
	CMakeLists.txt
yjxiong and others added 30 commits April 27, 2016 14:59
* init cudnn_v5 support

* Fix cudnn bn implementation

* cpu bn changes. cudnn frozen support.

* remove older bn related changes.

* Fix frozen backward

* Unit test for BN and cudnn BN layers

* update bn_convert script

* typo

* typo

* add epsilon option

* document updates
* Fix boost shared_ptr issue in python interface

* Default output model name for bn convert style script

* Fix bugs in generation bn inference model

* Script to convert inner product to convolution

* Script to do polyak averaging
* Specify whether bottom and top blobs are sharing data

* Reuse data memory if not propagate down

* Skip a layer if no_mem_opt is set

* Fix a bug and add optimize_mem enum

* Code formatting
Conflicts:
	src/caffe/layers/cudnn_bn_layer.cu
* improvise memory opt configs

* take care of share data with excluded blob
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

Successfully merging this pull request may close these issues.