Commit Graph

1987 Commits

Author SHA1 Message Date
thebhatman d6608682fc Suggested changes made 2019-03-05 16:18:50 +05:30
Manjunath Bhat 29b853e0bb
Made sure Gradients are not lost. 2019-03-04 22:17:19 +05:30
Manjunath Bhat 922e9c9bc2
Updated docs with AlphaDropout 2019-03-04 01:10:12 +05:30
Manjunath Bhat b5533ee00b
Exported AlphaDropout 2019-03-04 01:09:05 +05:30
Manjunath Bhat 97f874abcf
Added AlphaDropout which is used in SNNs. 2019-03-04 01:05:46 +05:30
Manjunath Bhat 704be49483
Added support for Float64 for DepthwiseConv
DepthwiseConv was giving errors for Float64. This fixes the issue.
2019-03-01 15:04:05 +05:30
Mike Innes 4cf43c0c41 simpler/nicer training loop 2019-02-28 14:58:42 +00:00
Mike Innes cd091ad005 in place implicit gradients 2019-02-28 14:08:01 +00:00
Mike Innes 8b4bc7cc52 organise params 2019-02-28 13:44:54 +00:00
Dhairya Gandhi 6825639f79 mapreduce for onehotmatrix 2019-02-28 09:17:18 +05:30
Mike J Innes d6cf116a74
Merge pull request #639 from ropenta/master
Added an example of Conv to Flux.jl/src/layers/conv.jl, and clarified…
2019-02-25 14:35:38 +00:00
Rohith Pentaparthy 1b1dff1266 Added an example of Conv to Flux.jl/src/layers/conv.jl, and clarified what WHCN means 2019-02-23 14:31:27 -06:00
Sklan 7463f09591
Update normalise.jl 2019-02-21 23:56:19 +05:30
Sklan 6044421c5c
Update normalise.jl 2019-02-20 13:47:31 +05:30
Lyndon White ebf50f4e1c Create performance tips docs section (#615)
* Create performance_tips.jl

* Rename performance_tips.jl to performance_tips.md

* add perf tips

* Update docs/src/performance_tips.md

Co-Authored-By: oxinabox <oxinabox@ucc.asn.au>

* Update docs/src/performance_tips.md

Co-Authored-By: oxinabox <oxinabox@ucc.asn.au>

* Update make.jl

* Update and rename performance_tips.md to performance.md

* spelling

* Update docs/src/performance.md

Co-Authored-By: oxinabox <oxinabox@ucc.asn.au>

* Update docs/src/performance.md

Co-Authored-By: oxinabox <oxinabox@ucc.asn.au>

* Update performance.md

* Update performance.md

* Update docs/src/performance.md

Co-Authored-By: oxinabox <oxinabox@ucc.asn.au>

* Update docs/src/performance.md

Co-Authored-By: oxinabox <oxinabox@ucc.asn.au>
2019-02-19 15:03:41 +00:00
Dhairya Gandhi 78876a14b3
Merge pull request #522 from kolia/tiny_stack_bugfix
Tiny bugfix: `stack` was still calling julia 0.6 `cat`
2019-02-15 20:50:08 +05:30
Dhairya Gandhi eb9da4084f
remove spurious line change 2019-02-15 20:33:21 +05:30
Dhairya Gandhi c50ad6cdb5
Merge branch 'master' into tiny_stack_bugfix 2019-02-15 20:20:01 +05:30
Ayan Banerjee 08b87e0bce Transition to doctests (#616)
* basics.md: Initial doctest to an example

Related to https://github.com/FluxML/Flux.jl/issues/561

* make.jl: Allow doctest to run

* Fix comments in order to pass doctests

* basic.md: Add doctests to examples
2019-02-14 18:29:27 +00:00
pshashk b0a5844afb Remove dims=1 from normalise (#619)
* remove `dims=1`

* add dims arg

* fix test

* remove dims=1 only from deprecated version
2019-02-11 16:11:47 +00:00
Dhairya Gandhi 2ec35861b5 removing non-allocating functions and tests 2019-02-11 21:22:32 +05:30
Dhairya Gandhi d16ef75b1c remove duplicate allowscalar call 2019-02-11 20:32:23 +05:30
Dhairya Gandhi 1ada9afe81 assert no scalar indexing for onecold 2019-02-09 22:38:49 +05:30
Dhairya Gandhi 35cd9761a8 adding tests 2019-02-09 22:32:02 +05:30
Mike J Innes f17a5acd2b
Merge pull request #606 from pshashk/patch-3
Add `corrected` argument to std
2019-02-08 19:09:33 +00:00
pshashk b074b2491a
fix docstring 2019-02-08 21:49:53 +03:00
pshashk c3e04392d8
drop dims type restriction 2019-02-08 16:15:37 +03:00
pshashk ae10421bfe
fix normalise test for dims kwarg 2019-02-08 16:02:03 +03:00
pshashk 911c901294
`dims` kwarg 2019-02-08 16:00:32 +03:00
pshashk 37385e0dbd
test normalise 2019-02-08 15:43:50 +03:00
pshashk 4f6432d133
test 2019-02-08 15:28:07 +03:00
pshashk 368c29e5e3
Add `corrected` argument to std
Fixes ffe037c485/src/layers/stateless.jl (L49)
2019-02-08 15:23:27 +03:00
Mike J Innes ffe037c485
Merge pull request #603 from FluxML/kf/namedtupletree
Treat NamedTuple like Tuple for treelike purposes
2019-02-08 11:06:12 +00:00
Mike J Innes 601e2d8ae0
Merge pull request #586 from KristofferC/kc/batchnorm
work around extreme slowdown in BatchNorm due to julia performance bug in broadcast fusion
2019-02-08 11:00:33 +00:00
Mike J Innes fe712bf338
Merge pull request #596 from IvanYashchuk/ivan/topic-issue-542
Fixed issue #542.
2019-02-08 10:38:23 +00:00
Ivan Yashchuk 6471790819 Pass symmetric matrix to `logdet` gradtest 2019-02-08 12:22:08 +02:00
Ivan Yashchuk e00ac88016 Added tracking of `logdet` and `logabsdet`. Added gradtests. 2019-02-08 09:55:33 +02:00
Keno Fischer 1e452a3042 Treat NamedTuple like Tuple for treelike purposes 2019-02-06 11:11:00 -05:00
Mike J Innes 57491b6c39
Merge pull request #602 from avik-pal/patch-2
Conv Transpose missing entry in the docs
2019-02-06 15:45:53 +00:00
Avik Pal c093d089a6
Add conv_transpose to docs 2019-02-06 21:11:41 +05:30
KristofferC 9914c531f6 work around extreme slowdown due julia performance bug 2019-02-06 16:19:29 +01:00
Mike J Innes 777571d4b4
Merge pull request #601 from FluxML/revert-591-onehot
Revert "Fix OneHotVector/Matrix performance on GPU"
2019-02-06 14:32:48 +00:00
Mike J Innes ecc55ec9e1
Revert "Fix OneHotVector/Matrix performance on GPU" 2019-02-06 14:31:15 +00:00
Mike J Innes e8b2ec6f67
Merge pull request #311 from tejank10/conv_transpose
2D Conv transpose support
2019-02-06 14:14:14 +00:00
Tejan Karmali cc4438cd93 Update NNlib to master in Manofest 2019-02-05 09:33:50 -05:00
Dhairya Gandhi 53875a85a1
Merge pull request #592 from MJ10/master
Layer normalisation for images
2019-02-05 18:51:02 +05:30
Moksh Jain 046f7b4eae fix std arguments in normalise 2019-02-05 18:36:04 +05:30
Ivan Yashchuk f790fff59a Use other definition for grad(det(A)). 2019-02-05 14:36:28 +02:00
Moksh Jain c6409d7686 add support for n-dimensional input to normalise layer 2019-02-05 17:09:22 +05:30
Ivan Yashchuk aa64d2157d Fixed issue #542.
Added tracking of LinearAlgebra.det and its grad method.
2019-02-05 11:38:27 +02:00