- 04 Jan, 2016 1 commit
-
-
Davis King authored
the number of threads and blocks rather than using the hard coded numbers I had in there. This makes some functions noticeably faster. Also added a dot() function that is fully asynchronous.
-
- 02 Jan, 2016 1 commit
-
-
Davis King authored
-
- 01 Jan, 2016 3 commits
-
-
Davis King authored
-
Davis King authored
networks. This revolved mostly around removing really deep template recursions since that upsets the compiler when you make really deep networks.
-
Davis King authored
-
- 31 Dec, 2015 3 commits
-
-
Davis King authored
method to more efficiently give the input gradient in some instances.
-
Davis King authored
network is allocated on the heap rather than resulting in really large stack usage for large networks.
-
Davis King authored
-
- 25 Dec, 2015 1 commit
-
-
Davis King authored
-
- 24 Dec, 2015 9 commits
-
-
Davis King authored
tensors with different sizes and it will zero pad them as needed.
-
Davis King authored
-
Davis King authored
define combination layers made out of other combination layers without being hassled by the compiler.
-
Davis King authored
-
Davis King authored
-
Davis King authored
-
Davis King authored
-
Davis King authored
in-place/out-of-place logic present.
-
Davis King authored
-
- 23 Dec, 2015 4 commits
-
-
Davis King authored
to the range [0,1].
-
Davis King authored
-
Davis King authored
symmetry between the non-inplace version. This also enables additional optimizations in the resulting network.
-
Davis King authored
since that's a little different in cuDNN. I also removed my CUDA code for doing batch normalization and replaced it with cuDNN's new batch normalization methods. Finally, I forgot to add a convolutional option to the bn_ object. Now it has one so you can set the mode however you like, either BATCH_NORM_FC or BATCH_NORM_CONV.
-
- 17 Dec, 2015 2 commits
-
-
Davis King authored
-
Davis King authored
it to use the saved average mean and invstd to scale the data instead of normalizing the batch.
-
- 16 Dec, 2015 1 commit
-
-
Davis King authored
-
- 15 Dec, 2015 1 commit
-
-
Davis King authored
with other parts of the library.
-
- 14 Dec, 2015 3 commits
-
-
Davis King authored
-
Davis King authored
-
Davis King authored
-
- 13 Dec, 2015 8 commits
-
-
Davis King authored
-
Davis King authored
-
Davis King authored
-
Davis King authored
spec says it should.
-
Davis King authored
-
Davis King authored
-
Davis King authored
-
Davis King authored
-
- 12 Dec, 2015 3 commits
-
-
Davis King authored
-
Davis King authored
cudnnAddTensor() function and updated the specs and asserts accordingly.
-
Davis King authored
kernel was still running.
-