diff options
author | Sam Gross <sgross@fb.com> | 2016-02-25 01:18:13 +0300 |
---|---|---|
committer | Sam Gross <sgross@fb.com> | 2016-02-25 22:50:15 +0300 |
commit | c327f5b86ad7972f12fd5fe41c7215eea381043d (patch) | |
tree | 0edeaee6e9e069b069ae4feddd44dea60c1accaa /THNN.lua | |
parent | 00a60967687741ffdac20a8dda924127f8ccae4e (diff) |
Add VolumetricBatchNormalization
The BatchNormalization modules now all extend nn.BatchNormalization and
use the same THNN/THCUNN implementation.
Diffstat (limited to 'THNN.lua')
-rw-r--r-- | THNN.lua | 4 |
1 files changed, 2 insertions, 2 deletions
@@ -474,7 +474,7 @@ TH_API void THNN_(TemporalSubSampling_accGradParameters)( int kW, int dW, real scale); -TH_API void THNN_(SpatialBatchNormalization_updateOutput)( +TH_API void THNN_(BatchNormalization_updateOutput)( THNNState *state, THTensor *input, THTensor *output, @@ -487,7 +487,7 @@ TH_API void THNN_(SpatialBatchNormalization_updateOutput)( bool train, double momentum, double eps); -TH_API void THNN_(SpatialBatchNormalization_backward)( +TH_API void THNN_(BatchNormalization_backward)( THNNState *state, THTensor *input, THTensor *gradOutput, |