https://github.com/Microsoft/CNTK
Revision a01f8cdb376e07be5a36034b84fc54bb339a1376 authored by Yuqing Tang on 14 September 2017, 20:01:55 UTC, committed by Yuqing Tang on 14 September 2017, 20:01:55 UTC
        Add python side work-around to allow the combination of mean gradient and specifying number samples with the right implementation; in Python, achieve the legacy logic of having per sample learning rate with mean gradient by overriding the per sample learning rate with ignored_minibatch_size. Also clarification in docstring.
1 parent d9b0da2
History
Tip revision: a01f8cdb376e07be5a36034b84fc54bb339a1376 authored by Yuqing Tang on 14 September 2017, 20:01:55 UTC
Squashed commit of the following:
Tip revision: a01f8cd
File Mode Size
Dependencies
Documentation
Examples
Manual
PretrainedModels
Scripts
Source
Tests
Tools
Tutorials
bindings
.clang-format -rw-r--r-- 931 bytes
.gitattributes -rw-r--r-- 3.3 KB
.gitignore -rw-r--r-- 7.2 KB
.gitmodules -rw-r--r-- 211 bytes
CNTK.Common.props -rw-r--r-- 1.6 KB
CNTK.Cpp.props -rw-r--r-- 11.7 KB
CNTK.sln -rw-r--r-- 213.2 KB
CONTRIBUTING.md -rw-r--r-- 210 bytes
CppCntk.vssettings -rw-r--r-- 10.0 KB
LICENSE.md -rw-r--r-- 7.9 KB
Makefile -rw-r--r-- 57.8 KB
README.md -rw-r--r-- 5.0 KB
configure -rwxr-xr-x 34.5 KB

README.md

back to top