Commit Graph

952 Commits

Author SHA1 Message Date
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
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