index
:
platform/upstream/caffeonacl
accepted/tizen_5.0_unified
accepted/tizen_5.5_unified
accepted/tizen_5.5_unified_mobile_hotfix
accepted/tizen_5.5_unified_wearable_hotfix
accepted/tizen_unified
armcl-v18.11
master
sandbox/daeinki/armcl-v18.08
sandbox/nmerinov/llvm
tizen
tizen_5.0
tizen_5.5
tizen_5.5_mobile_hotfix
tizen_5.5_tv
tizen_5.5_wearable_hotfix
Domain: Machine Learning / ML Framework; Licenses: BSD-2-Clause;
Inki Dae <inki.dae@samsung.com>
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
src
/
caffe
/
layers
/
tanh_layer.cu
Age
Commit message (
Expand
)
Author
Files
Lines
2014-11-19
fixed tanh to not return NaN for input values outside the range [-40, 40]
Sean Bell
1
-2
/
+1
2014-10-10
fix instantiation
Yangqing Jia
1
-1
/
+1
2014-09-19
fix types of (Layer)SetUp, Reshape, Forward, and Backward calls
Jonathan L Long
1
-5
/
+5
2014-08-13
Generalize loss by allowing any top blob to be used as a loss in which
Jeff Donahue
1
-2
/
+1
2014-08-06
LICENSE governs the whole project so strip file headers
Evan Shelhamer
1
-1
/
+0
2014-06-26
change Backward interface: propagate_down is a vector -- use to fix
Jeff Donahue
1
-2
/
+2
2014-06-05
Make TanH cleaner, more efficient, and possible to use in-place
Jeff Donahue
1
-13
/
+7
2014-03-27
Standardize copyright, add root-level CONTRIBUTORS credit
Evan Shelhamer
1
-1
/
+1
2014-03-19
change specification of forward/backward function and fix layer
Jeff Donahue
1
-3
/
+3
2014-03-18
addd CUDA_KERNEL_LOOP macro
blackball
1
-4
/
+2
2014-02-26
Splitting source files between CUDA and CPU code.
Eric Tzeng
1
-33
/
+0
2014-02-26
cpplint.py -> cpp_lint.py and NOLINT_NEXTLINE -> NOLINT_NEXT_LINE
Jeff Donahue
1
-2
/
+2
2014-02-26
fix most linter errors
Jeff Donahue
1
-3
/
+9
2014-02-26
Added tanh activation function layer.
Aravindh Mahendran
1
-0
/
+97