Tejan Karmali
e54df2de06
Merge branch 'master' into conv_transpose
2019-02-02 10:20:45 +05:30
Kristoffer Carlsson
fd0f1c7a82
use uncorrected standard deviation in normalise
...
fixes https://github.com/FluxML/Flux.jl/issues/529
2019-01-30 17:42:19 +01:00
Kristoffer Carlsson
f60079d07c
add hash verification to datasets
2019-01-30 13:11:26 +01:00
Mike J Innes
0469394715
Merge pull request #576 from mcabbott/patch-1
...
PermutedDimsArray
2019-01-29 14:55:55 +00:00
Mike J Innes
9e553adbf7
add hessian
2019-01-29 08:37:30 +00:00
Michael Abbott
031d1b3d57
PermutedDimsArray like permutedims
...
e.g. PermutedDimsArray(rand(2,3) |> param, (2,1))
2019-01-28 18:15:32 +01:00
Mike J Innes
0f8a4a48c6
extend update! with an optimiser
2019-01-28 14:10:09 +00:00
Mike J Innes
0f2975d905
update -> apply
2019-01-28 13:59:23 +00:00
Mike J Innes
bf0b5c5cef
Merge pull request #535 from asbisen/master
...
fixed stack/unstack function - in utils.jl for v1.0
2019-01-28 12:23:07 +00:00
Mike Innes
af8fdcc7af
fix #573
2019-01-28 10:54:58 +00:00
Mike J Innes
013b421b08
Merge pull request #570 from avik-pal/ap/batchnorm_fixes
...
Patches for default initializers
2019-01-28 10:40:55 +00:00
Mike Innes
1c3a63c42f
fixes #574
2019-01-28 10:11:07 +00:00
Mike J Innes
58ac415f6b
forward mode
2019-01-25 16:14:24 +00:00
Mike J Innes
2b1a3e92da
mapparams
2019-01-25 10:11:46 +00:00
Mike J Innes
791939709b
numeric precision utilities
2019-01-25 10:06:37 +00:00
Mike J Innes
1cf37ab9eb
rm some old deprecations
2019-01-25 09:54:32 +00:00
Avik Pal
733879681e
Change initializer to glorot_uniform
2019-01-24 18:48:30 +05:30
Avik Pal
bb72c528e1
Change initializers to Float32
2019-01-24 18:43:39 +05:30
Mike Innes
ca1c73ed35
fixup
2019-01-24 11:15:57 +00:00
Kristoffer Carlsson
325e3a4f70
clarify docs on single batch image to conv
...
fixes #309
2019-01-24 11:24:10 +01:00
Mike J Innes
62d780c77f
onecold fix
2019-01-24 10:16:41 +00:00
chengchingwen
06003b72c7
noise shape for dropout
2019-01-22 23:51:38 +08:00
Dhairya Gandhi
4be08fe194
remove debug statement
2019-01-22 17:29:12 +05:30
Mike J Innes
152ce4a164
conversions for dual numbers
2019-01-22 10:07:42 +00:00
Mike J Innes
496dbfabd2
make chain collectable
2019-01-22 00:31:55 +00:00
Mike J Innes
f6397e7358
Merge pull request #517 from FluxML/fix_adamw
...
Fix decay argument in ADAMW
2019-01-18 10:06:23 +00:00
Mike J Innes
058b4dc7fb
Merge pull request #557 from dhairyagandhi96/dg/transpose
...
fix transpose/ adjoint gradient
2019-01-16 15:46:44 +00:00
Mike J Innes
9d56807bcd
cuarrays version check
2019-01-15 11:43:57 -05:00
Dhairya Gandhi
0060cc3453
fixes transpose/ adjoint gradient
2019-01-15 21:59:32 +05:30
Mike J Innes
a3e0de1ee5
fixes #516
2019-01-15 15:49:18 +00:00
Mike J Innes
67d9016319
Merge pull request #538 from KristofferC/kc/promote
...
fix promotion by avoiding integer division in mse and crossentropy
2019-01-15 13:20:46 +00:00
Kristoffer Carlsson
c74aa67c5d
fix promotion by avoiding integer division in mse and crossentropy
...
oops
add tests
2019-01-15 14:15:05 +01:00
Mike J Innes
827a7b8ed5
Merge pull request #546 from ChrisRackauckas/random
...
Support random numbers as constants
2019-01-11 10:06:54 +00:00
Mike J Innes
aa1b4f410f
simplify
2019-01-11 10:06:14 +00:00
Christopher Rackauckas
f6faa10ee2
remove non-type dispatches
2019-01-10 08:57:10 -08:00
Mike J Innes
f0d5624ed2
Merge pull request #493 from dhairyagandhi96/master
...
[WIP] New Optimiser Docs
2019-01-10 11:10:38 +00:00
Dhairya Gandhi
4291c1a833
pull master
2019-01-10 16:35:57 +05:30
Mike J Innes
e6f925f977
train docstring simplification
2019-01-10 11:05:21 +00:00
Dhairya Gandhi
f00e1cdedf
[docs] replace :stop with Flux.stop()
2019-01-10 16:34:07 +05:30
Mike J Innes
735b970c12
fix update for scalars
2019-01-10 10:19:05 +00:00
Christopher Rackauckas
3ee5a99794
hit all possibilities
2019-01-09 23:15:21 -08:00
Christopher Rackauckas
cf061e9207
support random numbers as constants
2019-01-09 23:04:12 -08:00
Dhairya Gandhi
7484c54f03
fix train! API syntax docstring
2019-01-08 00:32:55 +05:30
Anand Bisen
ec8dde79c3
fixed stack/unstack function - in utils.jl for v1.0
2019-01-03 17:32:11 -08:00
Mike J Innes
6b11c552f3
better h/vcat, fixes #378
2018-12-19 11:19:01 +00:00
Mike J Innes
cdfc97f7c6
fix fix_dec
2018-12-19 11:18:44 +00:00
Dhairya Gandhi
e48268ff06
fix argument name in ADAMW
2018-12-12 16:47:42 +05:30
Tejan Karmali
ed835f26fe
printing ConvTranspose layer
2018-12-09 12:50:09 -05:00
Tejan Karmali
1648414a5d
fixes for layer and test
2018-12-04 11:08:40 -05:00
Tejan Karmali
519c3db5c0
clean code
2018-11-28 11:48:53 -05:00
Tejan Karmali
95e490a2c5
merge conflict resolved
2018-11-28 11:10:22 -05:00
Tejan Karmali
89f2709b61
resolved conflicts
2018-11-28 11:07:43 -05:00
Tejan Karmali
bc9bda9a85
in accordance with conv_filter api
2018-11-28 10:55:21 -05:00
Tejan Karmali
10f3a8eae2
conv_filter api changes
2018-11-28 10:55:21 -05:00
Tejan Karmali
ca8ad63fb6
in accordance with conv_data api
2018-11-28 10:55:21 -05:00
Tejan Karmali
9c3e34b15f
conv_data grad api change
2018-11-28 10:55:21 -05:00
Tejan Karmali
a71ee386d0
1.0 fix for conv transpose
2018-11-28 10:55:21 -05:00
Mike J Innes
a32c8a2e60
Merge pull request #499 from willtebbutt/wct/leq
...
Deal with <= for TrackedReals
2018-11-28 00:37:32 +00:00
Mike J Innes
dd154ca049
Merge pull request #294 from avik-pal/cudnn_batchnorm
...
Wrapper for CuDNN BatchNorm
2018-11-27 23:51:32 +00:00
Mike J Innes
1c36504768
fixup
2018-11-27 18:44:07 -05:00
Mike J Innes
7992de5cba
update requires syntax
2018-11-27 18:31:05 -05:00
Avik Pal
1d5b3429ea
Missing brackets
2018-11-20 09:26:48 +05:30
Will Tebbutt
c7f5026bd9
Deal with <= for TrackedReals
2018-11-18 13:06:32 +00:00
Mike J Innes
3d41dca338
immutable chain
2018-11-16 12:22:15 +00:00
Mike J Innes
6ac5345339
better printing
2018-11-14 23:53:30 +00:00
Mike J Innes
325035cf60
array conversions
2018-11-14 23:48:32 +00:00
Christopher Rackauckas
f20fa65848
Add missing eps overload for TrackedReal
...
`eps` can be called on the number type as well, and this is missing from the TrackedReal overloads.
2018-11-14 09:58:41 -08:00
Avik Pal
dfd680646c
Fix conflict
2018-11-14 22:18:57 +05:30
Mike J Innes
3ef6bfc0ac
Merge pull request #473 from avik-pal/patch-2
...
Update CUDNN function calls
2018-11-14 16:07:02 +00:00
Mike J Innes
cbc29c889a
old cuarrays compat
2018-11-14 10:53:26 -05:00
Mike J Innes
a57f66e58a
adapt updates
2018-11-14 15:36:18 +00:00
Mike J Innes
b3331205d1
faster default gradient performance
2018-11-12 23:39:25 +00:00
Mike J Innes
75ecc0b6ba
downconversion for conv
2018-11-12 20:21:27 +00:00
Mike J Innes
903db70673
float32 param initialisers
2018-11-12 20:10:47 +00:00
Dhairya Gandhi
1ea8c5a293
[WIP] add docstrings and doc improvements
2018-11-12 19:17:10 +05:30
Avik Pal
d6aacf4135
Fix reshape
2018-11-10 11:43:49 +05:30
Avik Pal
e2ae8b4e8d
Fix dimensions
2018-11-10 11:35:58 +05:30
Avik Pal
3bc809f49e
dropdims to make the array 2d
2018-11-10 11:25:37 +05:30
Avik Pal
4d703b31a1
Reshape 2D tensors to use cudnn batchnorm
2018-11-08 19:23:07 +05:30
Avik Pal
564518e448
Merge branch 'master' of https://github.com/FluxML/Flux.jl into cudnn_batchnorm
2018-11-08 19:13:34 +05:30
Avik Pal
02efc264e7
Fix unintentional change to spaces
2018-11-08 19:12:38 +05:30
Mike J Innes
30486f9c03
Merge pull request #441 from Paethon/rm_initn
...
Removes initn initialization
2018-11-08 13:25:02 +00:00
Mike J Innes
5e572df557
Merge pull request #485 from dhairyagandhi96/master
...
Add call back
2018-11-08 13:18:17 +00:00
Dhairya Gandhi
392c3c942b
re-add removed call function
2018-11-08 18:44:57 +05:30
Mike J Innes
a88b7528bf
constructor deprecations
2018-11-06 08:19:46 -05:00
Mike J Innes
0c19dad700
include cudnn.jl
2018-11-06 12:39:54 +00:00
Mike J Innes
39dcfd3933
Merge pull request #469 from invenia/ed/hang-draw-and-quarter
...
Stop type treason with show of the TrackedArray type
2018-11-06 11:54:07 +00:00
Mike J Innes
4763473079
fixed method
2018-11-06 11:50:04 +00:00
Mike J Innes
8042198475
Merge pull request #479 from dhairyagandhi96/master
...
Fix deprecations of optimisers
2018-11-05 13:01:59 +00:00
Mike J Innes
d071014fae
Merge pull request #448 from JobJob/adam-match-paper
...
Match paper for Adam implementation and make epsilon use more consistent
2018-11-05 12:57:30 +00:00
Mike J Innes
d0e4fbb1e0
Merge branch 'master' into ed/diagm-pair
2018-11-05 11:51:29 +00:00
Mike J Innes
5df48fbc5d
fix
2018-11-05 11:49:38 +00:00
Eric Davies
6b0b51e390
Stop type treason with show of the TrackedArray type
2018-11-02 16:00:58 -05:00
Joel Mason
29832aca92
Move some epsilons about
2018-11-02 22:59:04 +11:00
Dhairya Gandhi
5ec70fe29d
allow array parameters to old optimisers
2018-11-01 22:17:54 +05:30
Mike J Innes
c71c610747
separate gradient library
2018-11-01 15:35:55 +00:00
Dhairya Gandhi
ca4e01ac26
use user defined decay in ADAMW
2018-11-01 15:58:40 +05:30
Dhairya Gandhi
58a6c3f225
fix deprecations
2018-11-01 15:02:00 +05:30
Avik Pal
4ba891f666
Remove unnecessary import
2018-11-01 09:37:48 +05:30
Avik Pal
c67e33f387
Make the changes backward compatible
2018-11-01 09:37:16 +05:30
Mike J Innes
43c5f90d93
Merge pull request #379 from dhairyagandhi96/master
...
New optimisers interface
2018-10-31 16:38:40 +00:00
Mike J Innes
46049b9f44
tweak update rule
2018-10-31 16:08:18 +00:00
Mike J Innes
554c4c7c7a
return Params from params
2018-10-31 15:50:08 +00:00
Mike J Innes
4a54d30cbf
correct SGD deprecation
2018-10-31 15:30:30 +00:00
Mike J Innes
bffaceee02
tweaks
2018-10-31 14:58:55 +00:00
Mike J Innes
70283e1971
Merge pull request #465 from FluxML/mji/once
...
Destroy AD graph when doing in-place gradients
2018-10-31 14:14:38 +00:00
Mike J Innes
9312536b96
Merge pull request #461 from Roger-luo/roger-patch-1
...
Support view for TrackedArray
2018-10-30 15:24:05 +00:00
Mike J Innes
77178b7d67
remove old-style definition and test
2018-10-30 14:21:22 +00:00
Avik Pal
7804d980b2
Update cudnn.jl
2018-10-30 01:08:21 +05:30
Dhairya Gandhi
bebf4eb95f
fixed ExpDecay update! rule
2018-10-29 23:12:24 +05:30
Keno Fischer
baf868e851
Add VERSION check around broadcast piracy
2018-10-28 16:07:26 -04:00
Dhairya Gandhi
32ce2d78b8
fixed ExpDecay test
2018-10-27 19:53:06 +05:30
Dhairya Gandhi
815e8c206d
decay fixes
2018-10-27 19:26:42 +05:30
Mike J Innes
b77433cdfd
0.7 fix
2018-10-27 12:23:14 +01:00
Eric Davies
9f9803eec6
Add new-style diagm to tracker
2018-10-26 14:44:59 -05:00
Roger-luo
e5d58699e6
fix and add test
2018-10-26 14:06:17 -04:00
Mike J Innes
c21d768b7c
destroy AD graph when doing in-place gradients
2018-10-26 16:57:19 +01:00
Tejan Karmali
a657c287d0
in accordance with conv_filter api
2018-10-26 11:31:34 -04:00
Avik Pal
b838c0bc04
Update the libcudnn_handle
2018-10-26 10:24:30 +05:30
Roger-luo
a3cda9016c
apply Mike's change
2018-10-25 13:48:33 -04:00
Roger-luo
5f99e5775a
fix #458
2018-10-24 15:40:10 -04:00
Tejan Karmali
387df8c095
conv_filter api changes
2018-10-24 13:28:22 -04:00
Tejan Karmali
fca93471b3
in accordance with conv_data api
2018-10-24 12:52:43 -04:00
Avik Pal
ec2c00783d
Add missing export for DepthwiseConv
2018-10-24 22:18:26 +05:30
Tejan Karmali
0dc4ec4d6b
conv_data grad api change
2018-10-24 07:04:49 -04:00
Tejan Karmali
f540a0daf7
merge with upstream
2018-10-23 13:40:06 -04:00
Avik Pal
2559e7b4e6
Fix merge conflicts
2018-10-23 21:53:29 +05:30
Mike J Innes
bbccdb3eec
Merge pull request #279 from avik-pal/depthwiseconv
...
Adds support for Depthwise Convolutions
2018-10-23 17:22:15 +01:00
Mike J Innes
96dbae2d20
Omega and Turing fix
2018-10-23 11:30:37 +01:00
Tejan Karmali
e9bf86dbff
Merge branch 'master' of https://github.com/FluxML/Flux.jl into conv_transpose
2018-10-19 02:08:25 -04:00
Sebastian Stabinger
94e5e9f993
Removes initn initialization
...
Is replaced with glorot_uniform for Conv following Keras
2018-10-17 17:11:16 +02:00
Avik Pal
3899907164
Update conv.jl
2018-10-11 21:39:35 +05:30
Dhairya Gandhi
1f0f2a5ac2
fixed DescentWeightDecay parameters
2018-10-11 10:21:29 +05:30
Dhairya Gandhi
d8394298bb
fix merge conflicts
2018-10-11 10:15:59 +05:30
Dhairya Gandhi
fe8c147f72
fixed weight decay definition
2018-10-11 10:07:16 +05:30
Mike J Innes
ab0763fd41
Merge pull request #428 from tejank10/rnn-fixes
...
[WIP] Fixes for RNN tests
2018-10-10 16:58:44 +01:00
Tejan Karmali
8987e2c423
rm comments
2018-10-10 11:55:10 -04:00
Tejan Karmali
6b4bbd4fce
reverted back the weights changes in rnndesc
2018-10-10 10:29:15 -04:00
Mike J Innes
9f6c3d5a2c
fixes #403
2018-10-10 12:26:03 +01:00
Tejan Karmali
7b3e9c35ad
changed index to view
2018-10-09 12:57:20 -04:00
JohnnyChen
de7623ac94
use variable assignment to do "copy"
2018-10-09 03:49:17 +08:00
JohnnyChen
eaacec852f
Bug fix
2018-10-09 03:40:02 +08:00
JohnnyChen
27fec15fcc
Add explicit copy(x::TrackedArray) method
2018-10-09 03:34:41 +08:00
Tejan Karmali
4d1a6c305b
fixed params getting zero
2018-10-08 13:59:29 -04:00
JohnnyChen
36f5f274a5
Support copy(::TrackedArray)
...
1. fix issue https://github.com/FluxML/Flux.jl/issues/416
2. change test code to pass the test: some broken tests are not broken now...
2018-10-09 01:53:32 +08:00
Mike J Innes
73385b5dbd
Merge pull request #372 from johnnychen94/issue-#354
...
Type restriction for Dense layer
2018-10-05 15:03:03 +01:00
Mike Innes
c6740c5cdd
fix unbroadcast
2018-10-05 14:14:43 +01:00
Mike J Innes
325d2ce212
Merge pull request #418 from c-p-murphy/add-fashion-mnist
...
Add FashionMNIST
2018-10-05 14:05:50 +01:00
Mike Innes
61fb6cdf05
jit macro
2018-10-05 14:02:00 +01:00
Mike Innes
69afdd61a6
avoid a warning
2018-10-05 13:59:58 +01:00
Mike Innes
bfe85e65f1
compose tweaks
2018-10-05 13:52:26 +01:00
Mike Innes
0f2019eba5
compose tweaks
2018-10-05 12:57:03 +01:00
Mike Innes
9bc9771a8d
tweaks
2018-10-05 12:43:03 +01:00
Mike Innes
4abe518599
newline fixes
2018-10-05 12:37:47 +01:00
Tejan Karmali
2ff54ee0fd
cudnn_available() update
2018-10-04 11:31:29 -04:00
Christopher Murphy
73a526b1de
reuse utils from mnist.jl
2018-10-03 12:40:24 -04:00
Mike J Innes
683bbec71c
Merge pull request #413 from mcabbott/patch-2
...
evaluate both 2-ary DiffRules only when needed
2018-10-03 12:02:12 +01:00
Mike J Innes
fe6793fde5
closes #411
2018-10-03 11:45:29 +01:00
Robert Luciani
252e34e173
1.0+ updates - indices to axes, Vector init with undef
2018-10-02 21:39:00 +02:00
Christopher Murphy
95d72d7f79
update comments
2018-10-02 15:31:44 -04:00
Christopher Murphy
aff4c7898e
add FashionMNIST
2018-10-01 15:26:26 -04:00
Dhairya Gandhi
b661db3797
added deprecations and compose
2018-10-01 05:30:53 +05:30
Michael Abbott
d25e05d9ee
evaluate both 2-ary DiffRules only when needed
2018-09-27 10:40:44 +02:00
Alex Bird
d131853587
add inv/ldivide/rdivide + test
2018-09-19 13:08:30 +01:00
Dhairya Gandhi
6665189ff1
added remaining optimizers and tests
2018-09-16 17:34:51 +05:30
Isaac Tay
e803117e25
updated loadparams! function
2018-09-15 16:45:04 +08:00
Avik Pal
eb9b408c0f
Merge branch 'master' into depthwiseconv
2018-09-15 10:21:31 +05:30
Mike J Innes
08fb9b7df1
Merge pull request #397 from FluxML/nest-bcast
...
Nested Derivatives of Broadcast
2018-09-14 20:23:28 +01:00
Mike Innes
d797999fc5
fix sentiment model
2018-09-14 18:10:24 +01:00
Dhairya Gandhi
63bc71698b
updated tests
2018-09-14 20:32:56 +05:30
Dhairya Gandhi
4860c1d48b
fixed white lines
2018-09-11 18:35:21 +05:30
Dhairya Gandhi
d933f2079b
pulled tracker from upstream
2018-09-11 18:30:24 +05:30
Avik Pal
7d06f654f0
Fix tests
2018-09-11 16:58:05 +05:30
Avik Pal
7e7a501efd
Fix tests
2018-09-11 16:32:14 +05:30
Avik Pal
c4f87ff15c
Minor fixes:
2018-09-11 16:21:55 +05:30
Avik Pal
7e83852862
Fixes
2018-09-11 15:58:17 +05:30
Avik Pal
5fd8ffa47e
CuRNN updates
2018-09-11 15:44:07 +05:30
Avik Pal
8bea60d980
Merge branch 'master' into cudnn_batchnorm
2018-09-11 15:34:25 +05:30
Tejan Karmali
e86365ed3f
1.0 fix for conv transpose
2018-09-08 15:44:06 -04:00
James Bradbury
e7783ace12
1.0 compat for normalise
2018-09-06 18:38:11 -07:00
Mike J Innes
6bbed07e96
enable nested broadcast
2018-09-07 02:05:03 +01:00
Dhairya Gandhi
0b440f16ff
Merge branch 'master' of https://github.com/FluxML/Flux.jl
2018-09-06 22:48:03 +06:00
Johnny Chen
44049ce00c
Merge branch 'master' into issue-#354
2018-09-06 09:39:31 -05:00
Mike J Innes
5e4ee827e9
Merge pull request #371 from johnnychen94/issue-#323
...
Fix issue #323
2018-09-06 15:28:15 +01:00
Mike J Innes
ec16a2c77d
todone: nicer syntax on 0.7
2018-09-05 15:55:08 +01:00
Mike J Innes
1e0fd07b09
use expand
2018-09-04 14:30:02 +01:00
Mike J Innes
e6be639436
Merge branch 'master' into HEAD
2018-09-04 14:03:46 +01:00
Mike J Innes
93c4a6b4b5
fixes #343
2018-09-04 13:37:54 +01:00
Mike J Innes
a2d2d068aa
initial sketch
2018-08-28 17:55:59 +05:30
Mike Innes
53be49b102
fix #377
2018-08-28 11:02:38 +01:00
Mike J Innes
fac06751ea
Merge pull request #361 from dhairyagandhi96/with_stop
...
Add stop() to train loop when callback conditions are met
2018-08-28 10:56:15 +01:00
Mike Innes
2ca189bc96
newlines
2018-08-28 10:54:50 +01:00
Dhairya Gandhi
89bca2d98d
remove merge conflicts
2018-08-28 15:14:12 +05:30
Dhairya Gandhi
a964debd8a
fixed example in docs
2018-08-28 15:02:47 +05:30
Johnny Chen
0c4fb9655a
Fix a bug
2018-08-25 15:12:01 +08:00
Johnny Chen
4ac76c35b0
fix MethodError for == and ≈
...
```julia
param([2]).^2 == [4.0]
ERROR: MethodError: ==(::TrackedArray{…,Array{Float64,1}}, ::Array{Float64,1}) is ambiguous. Candidates:
==(x::TrackedArray, y) in Main.Flux.Tracker at /Users/jc/.julia/dev/Flux/src/tracker/array.jl:63
==(A::AbstractArray, B::AbstractArray) in Base at abstractarray.jl:1686
Possible fix, define
==(::TrackedArray, ::AbstractArray)
```
2018-08-25 14:51:40 +08:00
Mike Innes
7d6ec2365f
fixes #367
2018-08-24 14:30:39 +01:00
Mike Innes
86cf22675f
rewrite broadcast
2018-08-24 14:07:08 +01:00
Mike Innes
e13d28a7a2
cruft
2018-08-24 13:44:21 +01:00
Dhairya Gandhi
c035fe22d7
added deprecation warning
2018-08-24 13:08:03 +05:30
Yueh-Hua Tu
634d34686e
Add new constructors and test
2018-08-24 10:31:13 +08:00
Mike J Innes
953280d57f
Merge pull request #364 from boathit/master
...
fix argmax and add test
2018-08-23 15:52:06 +01:00
Mike Innes
dcde6d2217
tweaks
2018-08-23 15:44:28 +01:00
Johnny Chen
c9d6b5648f
Fix issue #354
2018-08-23 21:56:32 +08:00
Johnny Chen
6743d52d08
Fix issue #354
2018-08-23 21:34:11 +08:00
Johnny Chen
7bfe431321
Fix issue #323
2018-08-23 20:58:58 +08:00
boathit
6c97846551
rename argmax as onecold
2018-08-23 20:47:43 +08:00
Mike J Innes
6c355e93d2
Merge pull request #363 from pshashk/patch-1
...
Fix repeat
2018-08-23 11:28:13 +01:00
Mike Innes
9d1d5187f3
fix activations for 1.0
2018-08-23 10:56:31 +01:00
boathit
33c901c191
redo
2018-08-23 16:01:42 +08:00
boathit
5dca80bd68
fix argmax and batch deprecations
2018-08-23 13:17:58 +08:00
Dhairya Gandhi
2f1a9847fa
deprecate :stop from optimizers; housekeeping
2018-08-22 21:25:26 +05:30
Dhairya Gandhi
a7ad620f01
exporting stop
2018-08-22 00:33:30 +05:30
Dhairya Gandhi
3d11322d37
fixed docstring and not exporting stop
2018-08-22 00:29:07 +05:30
Dhairya Gandhi
ed044e2df7
changes as requested
2018-08-21 23:22:20 +05:30
boathit
616ed194df
fix argmax and add test
2018-08-21 11:29:57 +08:00
Mike Innes
216d278e7b
fix mnist loader
2018-08-20 16:57:43 +01:00
Mike Innes
3cfecaa4db
test cleanup
2018-08-20 15:38:25 +01:00
Mike Innes
e68b8765b6
broadcast fixes
2018-08-20 14:41:46 +01:00
pshashk
1115eda6af
repeat fix
...
ERROR: UndefVarError: A not defined
2018-08-20 16:11:56 +03:00
Dhairya Gandhi
1af7a53e1f
housekeeping: removed commented code
2018-08-20 18:10:20 +05:30
Mike Innes
5a023a9ccc
WIP 1.0 support
...
closes #353
2018-08-20 13:08:04 +01:00
Dhairya Gandhi
756207e782
added docs
2018-08-20 14:20:33 +05:30
Dhairya Gandhi
51578177a5
removed arguments from StopException
2018-08-20 14:08:23 +05:30
Dhairya Gandhi
df22bc5c8f
removed argument from stop function
2018-08-20 14:02:09 +05:30
Dhairya Gandhi
06db6ed314
housekeeping: fixing typo
2018-08-20 13:48:28 +05:30
Dhairya Gandhi
394b4167ce
moving stop to Optimise
2018-08-20 13:43:08 +05:30
Dhairya Gandhi
06aad375fc
properly importing functions
2018-08-20 13:35:55 +05:30
Dhairya Gandhi
e239eb1105
properly importing functions
2018-08-20 13:30:05 +05:30
Dhairya Gandhi
1228e9c5e2
removed include statement
2018-08-19 22:55:14 +05:30
Dhairya Gandhi
9c98272cf0
catching exception
2018-08-19 17:38:00 +05:30
Dhairya Gandhi
257e2a7d2e
checking exception
2018-08-19 17:11:11 +05:30
Dhairya Gandhi
5c42c8689c
printing expception
2018-08-19 17:04:31 +05:30
Dhairya Gandhi
b0f83f93ff
exported StopException
2018-08-19 16:41:13 +05:30
Dhairya Gandhi
a53a5c8350
exporting stop
2018-08-19 15:31:33 +05:30
Dhairya Gandhi
fbd82a6925
added end
2018-08-19 15:19:45 +05:30
Dhairya Gandhi
8229c8e045
modified training loop
2018-08-19 15:17:07 +05:30
Dhairya Gandhi
2aa057ec08
fixed throwing exception
2018-08-19 14:54:54 +05:30
Dominique Luna
f2021d41ac
initn -> init
2018-08-18 14:18:50 -04:00
Dominique Luna
3f42301e07
recurrent bug fixes
2018-08-18 11:50:52 -04:00
Dhairya Gandhi
887bfad312
returning :stop
2018-08-18 08:28:47 +05:30
Dhairya Gandhi
65a5ecccd2
returning
2018-08-18 08:24:49 +05:30
Dhairya Gandhi
999b00b64d
fixed typo
2018-08-17 19:45:10 +05:30
Dhairya Gandhi
0524964400
fixed typo
2018-08-17 19:40:48 +05:30
Dhairya Gandhi
8ad72e51ea
added function to stop training
2018-08-17 19:33:51 +05:30
Dhairya Gandhi
24a3bce495
added stop to break training loop
2018-08-17 17:46:13 +05:30
femtocleaner[bot]
2d80f68087
Fix deprecations
2018-08-14 16:46:23 +00:00
Simon
a43127f881
fix copy_transpose!
2018-08-15 12:16:12 +02:00
ayush1999
4683e925d4
Final changes
2018-08-12 11:38:48 +01:00
Josh Christie
59bdff2cae
Test 0.7 and 1.0
2018-08-11 14:58:29 +01:00
Josh Christie
c8307a0627
Use @info for logging
2018-08-11 14:42:33 +01:00
Josh Christie
710a65fe72
Fix back scalar with a Ref and fix diagonal test
2018-08-11 14:36:33 +01:00
Avik Pal
5db7a3a3ad
Fix Optimizers
2018-08-11 18:23:47 +05:30
Avik Pal
355091b9d1
Merge removing conflicts
2018-08-11 18:01:27 +05:30
Josh Christie
837e03613f
Updates for julia 1.0
2018-08-11 13:23:02 +01:00
Avik Pal
d3c78a80be
Fix layers errors
2018-08-11 17:20:27 +05:30
Avik Pal
4bd13c448f
Add updates for julia0.7
2018-08-11 15:23:40 +05:30
Josh Christie
5186e3ba18
Updates for julia 1.0
2018-08-11 10:51:07 +01:00
Avik Pal
3b448ce1ac
Merge branch 'master' into cudnn_batchnorm
2018-08-11 15:02:55 +05:30
Avik Pal
3affed8ef0
Remove track_kw
2018-08-10 03:21:05 +05:30
Mike J Innes
62d594af43
out of place gradients for collect
2018-08-07 22:09:20 +01:00
Avik Pal
a0ec472a4b
Merge branch 'master' into depthwiseconv
2018-08-08 01:20:37 +05:30
Mike J Innes
7103a0ed7d
tweaks
2018-08-03 15:19:10 +01:00
pevnak
926411a449
removed most error, the only one in Fallbacks test persits
2018-08-03 15:14:25 +01:00
pevnak
c657d4e47f
fixed the sum as suggested by mike
2018-08-03 15:14:25 +01:00
Simon Mandlik
02f343d44d
fixed more dep warns, also in tests, but maximum, minimum and size in array.jl still need to be updated. As a result, some more tests may not pass for the time being
2018-08-03 15:14:25 +01:00
Simon Mandlik
0471c489e6
depwarns
2018-08-03 15:14:25 +01:00
pevnak
3510c837a8
zeros replaced by zero
2018-08-03 15:14:25 +01:00
pevnak
ea38c7dbea
some more changes
2018-08-03 15:14:25 +01:00
pevnak
d6f5baee39
fixed fixes proposed by Carlo
2018-08-03 15:14:25 +01:00
pevnak
8ab209126d
removed zeros fix
2018-08-03 15:14:25 +01:00
pevnak
e98538673a
updated sum to be compliant with latest beta. Removed some depwarns
2018-08-03 15:14:25 +01:00
Mike J Innes
e5b3d27016
track_kw should be unnecessary
2018-08-03 15:14:10 +01:00
Avik Pal
4d17a1a809
Merge branch 'master' into depthwiseconv
2018-08-03 19:41:50 +05:30
Avik Pal
6a41f823c8
Update track function
2018-08-03 19:06:05 +05:30
Avik Pal
b4ba7df03a
Merge branch 'master' of https://github.com/FluxML/Flux.jl into cudnn_batchnorm
2018-08-03 18:55:46 +05:30
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
Avik Pal
2cc0f112f1
Updates
2018-07-27 20:12:49 +05:30
Avik Pal
7dd5ec16c9
Fix
2018-07-17 11:22:12 +05:30
Avik Pal
531ecccd38
Error statement
2018-07-17 10:14:23 +05:30
Avik Pal
4035641f00
Remove imports
2018-07-17 10:06:26 +05:30
Avik Pal
0bb3eaa1f6
Update CUDNN Batchnorm with new Flux AD
2018-07-17 09:40:20 +05:30
Avik Pal
646db81f94
Pull BatchNorm CPU updates
2018-07-17 09:24:38 +05:30
CarloLucibello
071dcdda87
update docs
2018-07-16 07:32:13 +02:00
CarloLucibello
185e9148b6
fix cpu batchnorm
2018-07-16 07:11:33 +02:00
Avik Pal
2664a16556
Update as per new AD
2018-07-13 14:12:46 +05:30
Avik Pal
0aabf9d86b
Merge branch 'master' into depthwiseconv
2018-07-13 14:04:19 +05:30
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
Avik Pal
e3b10691d2
make cache optional param
2018-06-28 15:27:59 +05:30
Avik Pal
bcf094451c
Fix typo
2018-06-28 14:45:35 +05:30
Avik Pal
d0b79e71e2
fix load error
2018-06-28 14:27:50 +05:30
Avik Pal
7ac9e191cb
Revert 1 change
2018-06-28 14:25:22 +05:30
Avik Pal
5ccde88ce6
Minor fix for 5D support
2018-06-28 14:21:17 +05:30
Avik Pal
681d8c4dfc
Remove cache
2018-06-28 12:11:32 +05:30
Avik Pal
8f43258ab7
Get the batchnorm working without cache
2018-06-28 12:04:25 +05:30
Avik Pal
4916c8e6da
Add treelike for now
2018-06-27 14:54:49 +05:30
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
Avik Pal
24ba1c4e6c
Make changes as per the review
2018-06-23 11:02:41 +05:30
Mike J Innes
aea1e73cde
scalar gradients
2018-06-21 13:12:42 +01:00
Avik Pal
91850a8baf
Add missing path to curnn.jl
2018-06-20 18:46:42 +05:30
Avik Pal
deb4950261
Make cuDNN take only 4D arrays
2018-06-20 15:54:38 +05:30
Avik Pal
3339ad5181
Integrate cudnn BatchNorm with Flux
2018-06-20 15:50:30 +05:30
Avik Pal
714ca23aba
Change default value of epsilon to prevent CuDNN BatchNorm warnings
2018-06-20 12:11:22 +05:30
Avik Pal
185f34d9fe
Add working backward pass
2018-06-20 12:09:54 +05:30
Avik Pal
bc47d02b3f
Remove uncessary imports
2018-06-17 12:40:01 +05:30
Avik Pal
af5ab7f9ef
Fix Tensor Descriptor Bug
2018-06-17 12:28:02 +05:30
Avik Pal
c6dcf079ce
Update file structure and make function calls correct
2018-06-17 11:47:49 +05:30
Avik Pal
24d13ac326
Fix missing parenthesis
2018-06-12 21:32:56 +05:30
Avik Pal
f12e367cab
Adding untested backward pass code
2018-06-12 18:26:09 +05:30