Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/soumith/cudnn.torch.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat (limited to 'README.md')
-rw-r--r--README.md9
1 files changed, 6 insertions, 3 deletions
diff --git a/README.md b/README.md
index b850ff3..d46a83c 100644
--- a/README.md
+++ b/README.md
@@ -18,9 +18,12 @@ Modules are API compatible their [`nn`](https://github.com/torch/nn) equivalents
cudnn.SpatialConvolution(nInputPlane, nOutputPlane, kW, kH, dW, dH, padW, padH)
cudnn.SpatialMaxPooling(kW, kH, dW, dH, padW, padH)
cudnn.SpatialAveragePooling(kW, kH, dW, dH, padW, padH)
-cudnn.ReLU()
-cudnn.Tanh()
-cudnn.Sigmoid()
+
+-- the pointwise functions take an additional optional argument. if inplace=true then they do operations in-place without using any extra memory for themselves
+cudnn.ReLU(inplace[=false])
+cudnn.Tanh(inplace[=false])
+cudnn.Sigmoid(inplace[=false])
+
-- SoftMax can be run in fast mode or accurate mode. Default is accurate mode.
cudnn.SoftMax(fastMode [= false]) -- SoftMax across each image (just like nn.SoftMax)
cudnn.SpatialSoftMax(fastMode [= false]) -- SoftMax across feature-maps (per spatial location)