github.com/torch/nn.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Collapse)	Author
2017-07-11	parameters() uses torch.type instead of type	Nicholas Leonard

2017-02-15	Added noBias module for VolumetricConvolution and VolumtericFullConvolution	Shubham Jain

2016-12-01	Move make contiguous code from lua to C.	Gregory Chanan
	Exceptions are: 1) SparseLinear requires additional parameters to be passed in (e.g. nbatches), so it's not clear it's worth moving to C since it won't really simplify the binding code logic. 2) BatchNormalization requires "makeBatch", which isn't a trivial translation to C. 3) LookupTable requires "view" in C, which is already a TODO 4) SpatialUpSamplingBilinear requires "view" in C, which is already TODO
2016-05-06	Adding an optional extra input to SpatialFullConvolution and ↵	Frederic Besse
	VolumetricFullConvolution which can be used to dynamically set the output size, as an alternative to using the adj terms, which has the downside to be fixed at construction time.
2016-03-26	Change display order	Koustav Mullick
	Ideally while displaying the kernel (and likewise for padding, etc.), it should be of the format kT x kW x kH, as in the doc or normal Volumetric Convolution. Here it was of the format kW x kH x kT. This caused confusion to me while creating a model and thought it might to others as well.
2016-02-18	Add THNN conversion of VolumetricFullConvolution	Andreas Köpf

2016-02-17	Replacing implementation of VolumetricFullConvolution. Now works like ↵	Frederic Besse
	SpatialFullConvolution.
2016-02-09	lazy init	Sergey Zagoruyko

2016-02-03	Add THNN conversion of Volumetric* modules	Andreas Köpf

2015-12-01	refactoring Deconvolution -> FullConvolution	soumith