diff options
| author | Soumith Chintala <soumith@gmail.com> | 2014-12-19 02:36:12 +0300 |
|---|---|---|
| committer | Soumith Chintala <soumith@gmail.com> | 2014-12-19 23:28:13 +0300 |
| commit | ad958c0e268d876ee4d713510b8c3ef83b37bca0 (patch) | |
| tree | 0defbe1196f778c9fb3f79f5f6e7a1da9ae92cda /README.md | |
| parent | d290c4cb9d632120d3fba97caefb3afb961081bf (diff) | |
everything works with R2. all unit tests pass. Maxpooling has free zero-padding
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 4 |
1 files changed, 2 insertions, 2 deletions
@@ -16,8 +16,8 @@ Modules are API compatible their [`nn`](https://github.com/torch/nn) equivalents ```lua -- All inputs have to be 3D or 4D(batch-mode), even for ReLU, SoftMax etc. cudnn.SpatialConvolution(nInputPlane, nOutputPlane, kW, kH, dW, dH, padW, padH) -cudnn.SpatialMaxPooling(kW, kH, dW, dH) -cudnn.SpatialAveragePooling(kW, kH, dW, dH) +cudnn.SpatialMaxPooling(kW, kH, dW, dH, padW, padH) +cudnn.SpatialAveragePooling(kW, kH, dW, dH, padW, padH) cudnn.ReLU() cudnn.Tanh() cudnn.Sigmoid() |