83b998c39d
Restore purity
2019-09-08 16:15:35 +01:00
3c1ac84676
Merge pull request #842 from baggepinnen/patch-4
...
Add RADAM optimizer
2019-09-02 14:36:40 +01:00
fe2e3c3e6b
Add RADAM news entry
2019-08-30 17:08:16 +08:00
7e8021422d
Update Project.toml
2019-08-29 14:40:36 +01:00
cb3bfd72f3
Export RADAM from Optimise
2019-08-29 07:46:45 +08:00
27934c3674
Merge pull request #852 from FluxML/tb/cuarrays_dep
...
RFC: Replace Requires with direct CuArrays dependency.
2019-08-27 15:56:16 +01:00
61a8cfd6ee
libcudnn check fix
2019-08-27 15:41:23 +01:00
9cd97f06f7
define has_cuarrays when no cuda
2019-08-27 15:06:04 +01:00
9da32e5d78
pkg up
2019-08-27 15:04:20 +01:00
4fef9d8508
Don't depend on unreleased CuArrays.
2019-08-27 09:40:22 +02:00
6ad3cdd138
Replace Requires with direct CuArrays dependency.
2019-08-27 09:33:15 +02:00
6494f73c78
Merge #847
...
847: Fix CuArrays.libcudnn imports r=dhairyagandhi96 a=janEbert
Closes #846 .
Co-authored-by: janEbert <janpublicebert@posteo.net>
2019-08-25 09:51:45 +00:00
dec1b37e8e
Merge remote-tracking branch 'origin/master' into HEAD
2019-08-24 12:23:10 +02:00
978d7bf195
Fix CuArrays.libcudnn imports
2019-08-24 02:21:54 +02:00
3287cf23db
Add RADAM export
2019-08-19 13:07:39 +08:00
304b433daa
Add RADAM to tests
2019-08-19 13:01:14 +08:00
ebbad0d135
Add RADAM optimizer
2019-08-19 12:22:32 +08:00
aab3c4e052
Merge #837
...
837: Use `CuArrays.ones` instead `cuones` which is deprecated r=dhairyagandhi96 a=mimadrid
I
Co-authored-by: Miguel Madrid Mencía <miguel.madrid.mencia@gmail.com>
2019-08-12 05:36:29 +00:00
14affbc91b
Use `CuArrays.ones` instead `cuones` which is deprecated
2019-08-11 13:38:44 +02:00
7c111e7cde
fixes #645
...
fixes #831
2019-08-09 13:53:11 +01:00
109c278f74
Merge #835
...
835: Fix cuzeros deprecation r=dhairyagandhi96 a=Moelf
Co-authored-by: Moelf <jerryling315@gmail.com>
2019-08-09 10:33:55 +00:00
4d00957b36
Fix CuArray zeros deprecation
2019-08-06 22:23:21 +02:00
0a5ce0ed61
Merge pull request #827 from ChrisRackauckas/patch-3
...
Momentum doesn't need params
2019-07-31 23:36:40 -04:00
ed12d4e7c0
Momentum doesn't need params
2019-07-31 17:56:51 -04:00
bab618d168
Merge pull request #767 from oxinabox/patch-6
...
Some cleanup on performance tips docs
2019-07-11 16:11:44 +01:00
27904d349c
Update performance.md
2019-07-11 16:11:32 +01:00
174adf94d9
Merge pull request #805 from DrChainsaw/prefor-so-fix
...
Fix for #803
2019-07-11 16:02:54 +01:00
9b96a3d69b
Change to array due to "type definition not allowed inside a local scope"
2019-07-09 01:15:55 +02:00
16d5f2bc24
Add x to seen in prefor to avoid infinite recursion if passed something self-referential
2019-07-08 23:11:35 +02:00
b3bba4c566
Merge pull request #801 from quatrejuin/master
...
Fix lack of x
2019-07-08 13:00:58 +01:00
b24e05bb20
Fix lack of x
2019-07-02 13:15:54 -04:00
5689b39538
Create FUNDING.yml
2019-06-26 17:51:54 -04:00
e88440974b
Merge pull request #796 from dhairyagandhi96/nadam
...
Pick beta from the state - NADAM
2019-06-19 22:18:56 +01:00
dd9cdbef14
remove uncessary call to beta
2019-06-16 19:09:50 +05:30
67f18663d9
pick beta from state in NADAM
2019-06-16 19:06:59 +05:30
b47238eb74
Merge pull request #793 from amellnik/typos
...
Two minor typos in docs
2019-06-12 11:31:06 +05:30
e17999f19b
Two minor typos
2019-06-11 22:09:59 -07:00
1902c0e7c5
Merge #446
...
446: Added the SkipConnection layer and constructor r=MikeInnes a=bhvieira
I added a DenseBlock constructor, which allows one to train DenseNets (you can train ResNets and MixNets with this as well, only need change the connection, which is concatenation for DenseNets).
Disclaimer: I created the block for a 3D U-Net, so the assumption here is that whatever layer is inside the block, its output has the same spatial dimension (i.e. all array dimensions excluding the channel and minibatch dimensions) as the input, otherwise the connection wouldn't match. I'm not sure this matches the topology of every DenseNet there is out there, but I suppose this is a good starting point.
No tests yet, will add them as the PR evolve.
I'm open to suggestions! :)
Co-authored-by: Bruno Hebling Vieira <bruno.hebling.vieira@usp.br>
Co-authored-by: Mike J Innes <mike.j.innes@gmail.com>
2019-06-05 13:28:41 +00:00
b98075817c
Merge branch 'master' into DenseBlock
2019-06-05 14:27:47 +01:00
fe759ac43c
Update docs/src/performance.md
...
Co-Authored-By: Kristoffer Carlsson <kristoffer.carlsson@chalmers.se>
2019-05-28 14:19:56 +01:00
8ee6af1bee
Merge #762
...
762: CrossCor layer r=avik-pal a=ayush-1506
Same as #423 (which could be edited since I lost access to that github account).
Co-authored-by: ayush-1506 <ayush.shridhar1506@gmail.com>
2019-05-14 10:36:22 +00:00
98a027a505
typo
2019-05-14 02:56:12 -07:00
bfc5bb0079
rebase
2019-05-14 02:53:48 -07:00
f263f0c8ed
add to layer docs
2019-05-14 02:53:06 -07:00
0a2e288c3f
another small test
2019-05-14 02:53:06 -07:00
2161163a82
added crosscor
2019-05-14 02:52:28 -07:00
451b80da3d
add to layer docs
2019-05-14 02:50:18 -07:00
7c28f7f883
Merge branch 'crosscor' of https://github.com/ayush-1506/Flux.jl into crosscor
2019-05-14 02:47:28 -07:00
6b3cd825b9
Added SkipConnection to docs tentatively in Other General Purporse Layers
2019-05-13 16:43:14 -03:00
796a2957c9
Added news and removed type annotation from SkipConnection structure
2019-05-13 16:33:31 -03:00
Mosè Giordano