245563077b
cleaner API
2019-11-27 19:40:58 +05:30
1c0e9acc45
Update CuArrays to include the workspace fix.
2019-11-27 14:31:03 +01:00
90a38a3201
Merge #937
...
937: Fix Glorot initialization, add He initialization r=MikeInnes a=Sleort
Should fix #442 .
Adds He weight initialization as a bonus :-)
Co-authored-by: Troels Arnfred Bojesen <tr-ab@online.no>
2019-11-26 16:17:06 +00:00
fb4a48f970
Merge #943
...
943: Fixes #900 r=MikeInnes a=dhairyagandhi96
Thoughts on the test?
cc @MikeInnes
Co-authored-by: Dhairya Gandhi <dhairya@juliacopmuting.com>
2019-11-26 15:09:27 +00:00
59bb0d81b0
add TODO
2019-11-26 16:23:09 +05:30
4c69b44a7c
Merge pull request #940 from matsueushi/feature/cuda-logitbc
...
Fix logitbinarycrossentropy on CuArrays
2019-11-26 10:18:07 +00:00
c031ae1a94
correct channel value
2019-11-24 13:31:31 +05:30
fbb377a7b4
Merge pull request #941 from FluxML/tb/include_during_precompile
...
Don't include the CUDA module during precompilation.
2019-11-24 08:55:43 +01:00
5f21238d1a
no grad dims helper
2019-11-24 13:25:02 +05:30
4ece13c649
Don't include the CUDA module during precompilation.
...
If we do, we could end up replacing it at runtime.
2019-11-22 18:03:51 +01:00
a0314ce682
Fix logitbinarycrossentropy on CuArrays
2019-11-22 05:23:24 +00:00
3f97701d4c
Merge branch 'HEAD' into weight_init_patch
2019-11-20 13:25:32 +09:00
60a29abaf1
Merge branch 'weight_init_patch' into HEAD
2019-11-20 13:25:19 +09:00
3b83828e4e
Merge branch 'HEAD' into weight_init_patch
2019-11-20 13:24:48 +09:00
af96a197c1
Fix Glorot initialization
...
Should fix #442
2019-11-20 13:20:42 +09:00
5839e166f6
Merge pull request #860 from dsweber2/activations
...
Activations
2019-11-19 16:44:25 +00:00
2fa3e5673e
Merge pull request #924 from FluxML/tb/cuda_init
...
CUDA package initialization improvements
2019-11-19 16:48:45 +01:00
c45cec4cba
Simplify warning.
2019-11-19 16:05:41 +01:00
bd734ed957
Bump CUDA dependencies.
2019-11-19 15:55:25 +01:00
69bf84278f
Remove wrong warning.
2019-11-19 15:53:43 +01:00
4f73e434a4
Merge pull request #935 from baggepinnen/patch-4
...
Fix AMSGrad on GPU
2019-11-19 12:58:37 +00:00
2b80573248
Fix Glorot initialization, add He initialization
...
Should fix #442 .
Adds He weight initialization as a bonus :-)
2019-11-19 18:16:29 +09:00
8638bcdcd7
Merge #936
...
936: Avoid unnecessary conversion r=MikeInnes a=baggepinnen
This initialization works for both cpu and gpu
Co-authored-by: Fredrik Bagge Carlson <baggepinnen@gmail.com>
2019-11-19 09:05:23 +00:00
2da22f31f0
Avoid unnecessary conversion
...
This initialization works for both cpu and gpu
2019-11-19 16:31:04 +08:00
df7ffb0ef8
Fix AMSGrad on GPU
...
The previous initialization created a CPU array. Now, the same type of array as `x` is created.
2019-11-19 16:27:44 +08:00
eb41715d26
define manual rules
2019-11-19 13:30:33 +05:30
4530ac65c7
Fix Glorot initialization, add He initialization
...
Should fix the issue reported at https://github.com/FluxML/Flux.jl/issues/442 .
Adds He weight initialization as a bonus :-)
2019-11-19 16:50:40 +09:00
967cc1c175
Merge pull request #927 from heliosdrm/patch-1
...
Extend docs about `train!`
2019-11-18 12:22:16 +00:00
dea29532ef
Merge branch 'master' into activations
2019-11-15 17:19:43 -08:00
a0e3729679
Update docs/src/training/training.md
...
Co-Authored-By: Mike J Innes <mike.j.innes@gmail.com>
2019-11-15 21:17:45 +01:00
20eb840882
keeping activations separate
2019-11-15 12:03:08 -08:00
7eb6a0c98c
Merge #932
...
932: Travis: test on 1.0 r=MikeInnes a=MikeInnes
Co-authored-by: Mike J Innes <mike.j.innes@gmail.com>
Co-authored-by: Mike Innes <mike.j.innes@gmail.com>
2019-11-15 16:21:30 +00:00
e24215ca98
guard test on 1.0
2019-11-15 15:59:42 +00:00
665e441919
pkg up
2019-11-15 12:12:28 +00:00
9d6f6fdaa3
Merge pull request #926 from janEbert/bc-cuda-fix
...
Fix binarycrossentropy on CuArrays
2019-11-15 13:05:52 +01:00
2471596cdb
test on 1.0
2019-11-15 11:50:13 +00:00
89afa20410
Merge branch 'activations' of github.com:dsweber2/Flux.jl into activations
2019-11-14 14:09:27 -08:00
58c794702d
simpler test
2019-11-14 14:05:53 -08:00
0fe3ac4e77
bring activations into function call
2019-11-14 13:40:52 -08:00
db92b0e3ce
super simple test
2019-11-14 13:40:52 -08:00
6475f6a43e
recursive way of doing activations
2019-11-14 13:40:52 -08:00
99679f7e16
deal with empty Chain
2019-11-14 13:40:52 -08:00
d0202a2945
adding the extra commits broke the accumulate version
2019-11-14 13:40:52 -08:00
cdaaca8cfa
make activations zygote friendly
2019-11-14 13:40:29 -08:00
ba4e3be0d3
explanations about params in `train!`
2019-11-14 16:22:31 +01:00
074eb47246
Update training.md
2019-11-12 23:29:38 +01:00
e89b8eba77
fixes
2019-11-13 01:12:26 +05:30
7e1ffd6507
Extend docs about `train!`
...
Related to #921 : explain why it is not needed to pass the model as argument.
2019-11-08 21:39:00 +01:00
453ecd1f24
Merge remote-tracking branch 'upstream/master' into samepad
2019-11-08 18:49:47 +01:00
a00d8d94ec
Add test for CUDA binarycrossentropy
2019-11-08 17:28:54 +01:00
Dhairya Gandhi