TastyPancakes/Flux.jl
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,464 Commits 104 Branches 42 Tags 5.8 MiB
bffaceee02
Commit Graph

1056 Commits

Author SHA1 Message Date
Mike J Innes
e5b3d27016 track_kw should be unnecessary 2018-08-03 15:14:10 +01:00
Mike Innes
f5c9361617 matmul fix 2018-08-03 13:02:47 +01:00
Mike Innes
4cf6bac0c1 fix hook 2018-08-03 13:02:47 +01:00
Mike J Innes
70718e7a64 update treelike 2018-08-03 13:02:47 +01:00
Mike J Innes
d782b33701 syntax 2018-08-03 13:02:47 +01:00
Mike J Innes
85fd77d70a linalg deprecations 2018-08-03 13:02:47 +01:00
Mike J Innes
89872c5a8b val deprecations 2018-08-03 13:02:47 +01:00
Mike J Innes
474f578517 ObjectIdDict -> IdDict 2018-08-03 13:02:47 +01:00
Mike J Innes
aa209ee137 no longer needed 2018-08-03 13:02:47 +01:00
Mike J Innes
00cfe24d66 fix cat 2018-08-03 13:02:47 +01:00
Mike J Innes
adc216f182 fix broadcasting 2018-08-03 12:56:32 +01:00
Mike J Innes
e486c50610 fix data 2018-08-03 12:56:31 +01:00
Mike J Innes
fb8a220659 fix matmul 2018-08-03 12:56:31 +01:00
Mike J Innes
7057ca739e fix std usage 2018-08-03 12:56:27 +01:00
Mike J Innes
88a265154c deprecations 2018-08-03 12:54:31 +01:00
Mike J Innes
b18b51656c requires update 2018-08-03 12:54:24 +01:00
Mike J Innes
a49e2eae41 deprecated Void 2018-08-03 12:53:52 +01:00
Mike J Innes
1fd49c2a90 fix array show 2018-08-03 12:53:52 +01:00
Yueh-Hua Tu
5b37319289 Add Maxpool and Meanpool 2018-08-01 00:10:53 +08:00
Mike J Innes
a8ccc79f61 perf hacks 2018-07-30 20:08:44 +01:00
Mike J Innes
a0fd91b866
Merge pull request #307 from jarvist/master 
Add ADAMW "Fixing Weight Decay Regularization in Adam"
 2018-07-11 19:12:58 +01:00
Mike J Innes
dda51a0140 update docs 2018-07-11 15:31:22 +01:00
Mike Innes
10a169bb77 update cudnn rnn 2018-07-10 18:16:37 +01:00
Mike J Innes
70b5efeb4e basic nested AD 2018-07-10 09:03:09 +01:00
Mike J Innes
80af9a3830 broadcast efficiency 2018-07-09 23:40:07 +01:00
Mike J Innes
e763c342ee shave some memory 2018-07-09 19:44:14 +01:00
Mike J Innes
1430053b69 checkpoints 2018-07-09 17:52:34 +01:00
Mike J Innes
7778d17884 functional API 2018-07-09 16:57:44 +01:00
Mike J Innes
5e319c7395 fix gradient definitions 2018-07-09 13:39:10 +01:00
Mike J Innes
41b9412439 new grad api 2018-07-09 13:36:46 +01:00
Jarvist Moore Frost
344a750770 Merge branch 'master' of github.com:jarvist/Flux.jl into HEAD 2018-07-03 11:15:43 +01:00
Jarvist Moore Frost
aee4a83c55 Add ADAMW weight-decay. 
See http://www.fast.ai/2018/07/02/adam-weight-decay/ and the original
paper https://arxiv.org/abs/1711.05101.pdf for context.

I don't know what I'm doing, and this is quite possibly wrong - but on
a simple Char-RNN I have lying around on my harddisk, this seems to
improve the rate of learning consistently for different hyperparameters
vs. standard ADAM with the same decay constant.
 2018-07-03 11:11:32 +01:00
Mike J Innes
ce88273880 gradient hook 2018-07-02 13:19:13 +01:00
Mike Innes
5d8b63dc65 avoid implementation details in docs 2018-06-29 13:53:50 +01:00
Matthew Kelley
864d72eef5 Overload Base.eps() for TrackedReal 2018-06-26 23:55:43 -06:00
Matthew Kelley
0e95be3326 Call Flux.Tracker.data() on ŷ for bce 2018-06-26 14:48:51 -06:00
Matthew Kelley
ed032cdb1e Change epsilon value to eps(ŷ) 2018-06-26 12:29:06 -06:00
Matthew Kelley
e08fd7a6d2 Added epsilon term to binarycrossentropy 2018-06-26 11:43:16 -06:00
Mike J Innes
88c16e62dd fixes #284 2018-06-26 15:09:26 +01:00
Mike J Innes
836e3872b6 style 2018-06-26 15:09:21 +01:00
Mike J Innes
2723c9ee04
Merge pull request #257 from staticfloat/sf/back_inf_nan 
Check for `Inf` and `NaN` within `back!(::TrackedReal)`
 2018-06-26 14:42:33 +01:00
Mike J Innes
0a04e3ba61 Chain activations 2018-06-26 14:30:46 +01:00
Mike J Innes
7726a5b605 inferrable 2018-06-26 14:12:57 +01:00
Mike J Innes
3b575930ca Merge branch 'master' into scalar_pad_stride 2018-06-26 14:05:07 +01:00
Mike Innes
7e3cf45ee4 better error 2018-06-25 11:36:52 +01:00
Mike J Innes
aea1e73cde scalar gradients 2018-06-21 13:12:42 +01:00
Tejan Karmali
d20771d6be
Default value of dilation 
dilation should be 1 by default
 2018-06-09 02:29:46 +05:30
Tejan Karmali
4a24b69976
Merge branch 'master' into nadam-opt 2018-06-08 16:54:41 +05:30
Mike J Innes
4915b0c8dd
Merge pull request #268 from staticfloat/patch-2 
Add `dilation` kwarg to `Conv`
 2018-06-07 13:49:02 +01:00
Mike J Innes
af8f3348eb
Merge pull request #270 from staticfloat/sf/tracked_repeat 
Add `TrackedArray` support for `repeat(x; inner, outer)`
 2018-06-06 17:34:58 +01:00
Mike Innes
2370bdbe91 see #205 2018-06-06 17:01:28 +01:00
staticfloat@gmail.com
f390a39d77 Add TrackedArray support for repeat(x; inner, outer) 2018-05-22 17:41:05 -07:00
Elliot Saba
e6efca4bf4 Add dilation kwarg to Conv 
Now that we have dilated convolution support in `NNlib`, this is enables support in Flux's `Conv` layer.
 2018-05-21 13:44:13 -07:00
James Bradbury
af12f006f2
Use broadcast for dropout 
Should be fast enough on GPU now that it's not going to be an optimization target again for a while. Hopefully isn't meaningfully slower on CPU?
 2018-05-20 04:04:33 -07:00
staticfloat@gmail.com
9fdbe843ef Check for Inf and NaN within back!(::TrackedReal) 
This is often checked for within user code, no reason to do that, let's
do it for them within `back!(::TrackedReal)`
 2018-05-07 15:30:44 -07:00
Mike J Innes
24ad384a38
Merge pull request #243 from gustafsson/catdim 
Support for hcat and cat
 2018-05-07 13:04:31 +01:00
Mike Innes
ef9077d9fa style 2018-05-07 13:03:52 +01:00
Mike Innes
b59161a41e export Tracker again 2018-05-05 17:15:18 +01:00
Johan Gustafsson
5fc6190956 RowVector tests 2018-05-02 16:10:39 +02:00
Johan Gustafsson
94bb064a0f more tests of array promotion for concatenation 
# Conflicts:
#	test/tracker.jl
 2018-05-02 16:00:29 +02:00
Johan Gustafsson
1c189c62ed cat with multiple dims #156 
Co-authored-by: americast <sayan.sinha@iitkgp.ac.in>
 2018-05-02 15:59:46 +02:00
Johan Gustafsson
fb68529169 define back function right after forward function 2018-05-02 15:59:46 +02:00
Johan Gustafsson
509a2e59f6 cat promotions and mixed ranks 2018-05-02 15:59:46 +02:00
Johan Gustafsson
eaaf5fd34c vcat arrays with ndims>2 2018-05-02 15:59:46 +02:00
Johan Gustafsson
bcef5c4ab5 Support hcat and cat 2018-05-02 15:59:46 +02:00
Mike J Innes
7d7d89569c rm this deprecation for 0.6 2018-05-01 12:20:36 +01:00
Mike J Innes
9a7e6e9c5c hold off on some things 2018-05-01 12:18:56 +01:00
CarloLucibello
e186b958dd more exports 2018-05-01 12:13:14 +01:00
Mike J Innes
ee89a7797e
Merge pull request #245 from freeboson/adamax 
Add AdaMax optimizer
 2018-05-01 11:28:07 +01:00
Mike J Innes
5efbaddb97
Merge pull request #249 from ninjin/nin/minimum 
[RFC] Backpropagation for `maximum` and `minimum`
 2018-04-30 18:40:42 +01:00
Mike J Innes
73a51400b6 better error message 2018-04-30 12:09:15 +01:00
Pontus Stenetorp
cfd29b9c76 Backpropagation for maximum and minimum 2018-04-29 13:52:54 +01:00
Sujeet Akula
8c042bd522
element wise max() 2018-04-26 21:12:31 +10:00
Sujeet Akula
5e5f255f81
export typo 2018-04-26 17:42:04 +10:00
Sujeet Akula
4586bda5ab
export/test adamax 2018-04-26 17:40:11 +10:00
Sujeet Akula
b6508e2416
add adamax 2018-04-26 17:37:24 +10:00
Mike J Innes
baff20514d gpu broadcast fix 2018-04-17 18:05:58 +01:00
Mike J Innes
8f73dc6e14 fix gpu cross entropy 2018-04-17 17:56:47 +01:00
tejank10
2ef25775c6 removed extra expand and fixed bug 2018-04-16 01:18:26 +05:30
Mike Innes
d12fb98f2a nicer batchnorm shape error 2018-04-15 20:29:25 +01:00
tejank10
2f5473d435 added expand in conv constructor 2018-04-16 00:59:11 +05:30
Mike J Innes
8f29968c32
Merge pull request #207 from safnuk/pull-request/07b0f95d 
BatchNorm for convolutions
 2018-04-15 20:10:33 +01:00
Mike J Innes
683a73fed3 download info 2018-04-15 20:09:30 +01:00
Mike J Innes
5fd240f525 interface tweaks 2018-04-15 20:04:42 +01:00
Mike J Innes
73a0be3e04 Merge branch 'master' into pull-request/07b0f95d 2018-04-15 17:10:29 +01:00
Mike J Innes
642543808e
Merge pull request #226 from CarloLucibello/reshape 
fix reshape
 2018-04-15 16:53:21 +01:00
tejank10
b080f5c82e Scalar pad and stride 2018-04-15 20:32:40 +05:30
Mike J Innes
cb3ae8df6a rename normalise.jl 2018-04-15 15:45:46 +01:00
Mike J Innes
b05e755068 rm jit from cuda 2018-04-15 15:08:58 +01:00
tejank10
5cc681317a added stride for pooling in tracker 2018-04-15 15:07:04 +01:00
tejank10
f6097d58d6 Scalar pad/stride for Conv constructor 2018-04-15 12:15:41 +05:30
Mike Innes
9d7164f15f we'll do this differently 2018-04-14 02:09:35 +01:00
tejank10
65847bb745 moved epsilon into sqrt 2018-04-04 15:25:20 +05:30
tejank10
3ead662987 Update rule fixed 2018-04-04 15:18:44 +05:30
CarloLucibello
b415333233 fix reshape 2018-04-02 16:09:57 -04:00
tejank10
ea9b5471fa NADAM optimizer 2018-04-03 01:27:22 +05:30
Brad Safnuk
b9a66c679d Fix error in initialization of σ. 2018-03-22 22:20:21 -04:00
Brad Safnuk
35299d4621 Fix type instability when loading onto a gpu. 
Also fixes Issue #216.
 2018-03-22 21:32:32 -04:00
Mike J Innes
4320738d87 fix 2018-03-21 11:25:47 +00:00
Mike Innes
1c5f8e3534 ndims for shapes 2018-03-16 14:42:08 +00:00
Brad Safnuk
db2d9efb72 Update BatchNorm documentation 2018-03-15 21:59:38 -04:00
Brad Safnuk
6653ec86d9 Allow multidimensional inputs to batchnorm. 
Can be used in conjunction with convolutional layers, in addition
to dense layers, with the same api.
 2018-03-15 21:48:59 -04:00
Mike J Innes
e931552f7d
Merge pull request #200 from chengchingwen/repmat 
implement `back` of `repmat`
 2018-03-15 15:18:48 +00:00
Mike J Innes
5d7edb5aaa
Merge pull request #197 from chengchingwen/master 
Implement `prod` for `TrackedArray`
 2018-03-15 15:17:24 +00:00
boathit
2ec37790be eliminate ambiguity 2018-03-13 10:50:56 +08:00
boathit
ff2caf032c eliminate ambiguous 2018-03-12 22:48:16 +08:00
Mike J Innes
9ccbac8b80 jit gpu support 2018-03-07 19:18:27 +00:00
chengchingwen
43af3895b0 change prod implementation to avoid small xs 2018-03-07 21:03:13 +08:00
chengchingwen
c00f7f850f implement back of repmat 2018-03-07 20:43:59 +08:00
chengchingwen
7c721475c6 add gradient check for prod and fix dims in back(::typeof(prod),...) 2018-03-07 16:24:44 +08:00
Mike Innes
d21c313ea7 tweaks 2018-03-06 19:58:47 +00:00
Mike Innes
36baa7ec2c convnet primitives 2018-03-06 19:58:05 +00:00
Mike Innes
0802b4d5cf closes #198 2018-03-06 16:56:01 +00:00
Elliot Saba
6445295318 Better download detection 2018-03-06 08:45:45 -08:00
Elliot Saba
19f691d342 Use cache.julialang.org to store ML models 
It's annoying that when third party servers go down our tests break.
Let's at least make sure that if our tests break due to server outages
it's our fault.
 2018-03-06 08:03:21 -08:00
Mike Innes
3babeeb440 scalar hashing 2018-03-06 13:49:05 +00:00
chengchingwen
86d782a5ce implement prod for TrackedArray 2018-03-06 18:01:19 +08:00
Mike Innes
c95a97f6ae make epochs available 2018-03-06 03:01:56 +00:00
Mike Innes
432b9c3222 loadparams! 2018-03-06 02:45:31 +00:00
Mike Innes
65ed95190a fix 2018-03-05 23:44:25 +00:00
Mike Innes
bfd6a4c0ec cleaner interrupts 2018-03-05 23:05:45 +00:00
Mike Innes
5153cde847 move epochs 2018-03-05 22:56:22 +00:00
Mike J Innes
662439c164 closes #177 2018-03-05 17:24:46 +00:00
Elliot Saba
36295799ee Add permutedims() for tracked arrays 2018-03-02 10:22:28 -08:00
Mike J Innes
8019f789f8 use normal log 2018-03-01 16:35:49 +00:00
Mike J Innes
ac57fc3c26 use @ fix in a few places 2018-03-01 16:31:20 +00:00
Mike J Innes
c2fea2acf6 revert this 2018-02-28 23:06:53 +00:00
Mike J Innes
2eb38eedbf update gpu api 2018-02-28 22:51:08 +00:00
Mike J Innes
ccef9f4dd4 jit softmax 2018-02-28 22:07:35 +00:00
Mike J Innes
7606b1a399 single-batch convolution 2018-02-28 14:25:32 +00:00
Mike J Innes
6bdc2b37a9 inline call 2018-02-28 13:47:14 +00:00
Mike J Innes
a401f08cda compile layers 2018-02-27 22:40:51 +00:00
Mike J Innes
5a32976cbf basic compile step 2018-02-27 21:43:41 +00:00
Mike J Innes
bdb8aae107 move cache logic 2018-02-27 21:41:03 +00:00
Mike J Innes
2c74976602 more general 2018-02-27 01:25:40 +00:00
Mike J Innes
466b5c501a cpu/gpu conveniences 2018-02-26 23:10:59 +00:00
Mike J Innes
15d1d3256b conv api updates 2018-02-26 22:43:07 +00:00
Mike J Innes
54919b8dca rm deprecation 2018-02-22 00:23:02 +00:00
Mike J Innes
491785a681 ignore state in mapleaves 2018-02-22 00:22:51 +00:00
Mike J Innes
ec65e2cec7 fix printing 2018-02-22 00:21:48 +00:00
Mike J Innes
af2e6b7e1d fix 2018-02-22 00:15:38 +00:00
Mike J Innes
99b739cf00 fixes #176 2018-02-21 23:21:20 +00:00
Mike J Innes
e3b4b16e01
Merge pull request #178 from schmrlng/pull-request/e6f55641 
Convert OneHot CuArrays to dense CuArrays before passing to CUDNN methods
 2018-02-21 22:34:11 +00:00
Mike J Innes
6bdd283fbd no longer necessary 2018-02-21 22:29:31 +00:00
Iblis Lin
043fedde3c
introduce Reexport 
- Reexporting NNlib

fix #180
 2018-02-21 16:55:20 +08:00
Ed Schmerling
e6f556411a Convert OneHot CuArrays to dense CuArrays before passing to CUDNN methods 2018-02-19 17:32:15 -08:00
Mike J Innes
4035745f6e may help numerical tests 2018-02-19 12:51:02 +00:00
Mike J Innes
989adcdc7d gpu fix 2018-02-17 12:41:53 +00:00
Mike J Innes
11511982a4 numerical stability 2018-02-17 11:56:03 +00:00
Mike J Innes
e5791bc5f6 frequencies utility 2018-02-17 11:19:51 +00:00