250aef5a5a
normalise test fixes
2019-09-10 16:19:55 +01:00
2f7ad895aa
test cleanups
2019-08-19 15:22:50 +01:00
9590aa63e3
rm last uses of param/data
2019-08-19 15:14:42 +01:00
8d6028e27a
tests with gradients
2019-07-12 20:47:43 +05:30
e2bf46b7fd
gpu test fixes
2019-07-12 14:52:01 +01:00
e6d5846e49
Temporary removal of Float16 test
2019-06-14 23:24:31 +05:30
1ff4e3188e
back on mse failing for Float16
2019-06-13 16:41:25 +05:30
c7c0ee2cbc
Resolving Merge Conflicts
2019-06-12 21:34:42 +05:30
a56cfb73c3
BatchNorm test corrected
2019-06-11 20:34:48 +05:30
f465665c73
Corrected test for asymmetric padding
2019-06-11 20:20:00 +05:30
94a2d1987d
Updated tests of normalisation layers.
2019-06-11 20:05:07 +05:30
b98075817c
Merge branch 'master' into DenseBlock
2019-06-05 14:27:47 +01:00
98a027a505
typo
2019-05-14 02:56:12 -07:00
bfc5bb0079
rebase
2019-05-14 02:53:48 -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
7c28f7f883
Merge branch 'crosscor' of https://github.com/ayush-1506/Flux.jl into crosscor
2019-05-14 02:47:28 -07:00
c5fc2fb9a3
Added tests
2019-05-13 16:32:00 -03:00
68ba6e4e2f
Merge #563
...
563: noise shape for dropout r=MikeInnes a=chengchingwen
I add the noise shape for dropout, similar to the `noise_shape` argument in [`tf.nn.dropout`](https://www.tensorflow.org/api_docs/python/tf/nn/dropout )
Co-authored-by: chengchingwen <adgjl5645@hotmail.com>
Co-authored-by: Peter <adgjl5645@hotmail.com>
2019-05-13 17:16:10 +00:00
2fc2a5282c
Merge remote-tracking branch 'upstream/master' into drop_shape
2019-05-14 00:50:59 +08:00
48fcc66094
Remove vestigial testing `println()`
2019-05-12 11:20:24 -07:00
2e6561bb6a
Change `DepthwiseConv()` to use `in=>out` instead of `in=>mult`.
...
This is an API change, but I think it makes more sense, and is more
consistent with our `Conv()` api.
2019-05-12 11:20:24 -07:00
5c5140683c
make dims as field of Dropout
2019-05-10 23:45:50 +08:00
99d07e67db
another small test
2019-05-09 16:43:28 +05:30
9a3aa18c17
conflicts
2019-05-08 11:56:46 +05:30
e96a9d7eaf
Switch broken #700 test to pass
2019-05-03 22:36:32 +02:00
73c5d9f25c
fix
2019-05-03 22:22:52 +02:00
27a9a7b9cf
add broken test for #700
2019-05-03 22:22:52 +02:00
5b79453773
passing tests... ish
2019-05-02 18:54:01 -07:00
0c265f305a
fix most tests
2019-05-02 18:52:09 -07:00
20b79e0bdf
added crosscor
2019-05-01 22:29:00 +05:30
6e22cd4931
Add asymmetric padding to convolutional layers
2019-04-25 09:55:23 -07:00
113ddc8760
Update `Flux` code for new NNlib branch
2019-04-25 09:55:23 -07:00
54d9229be9
Merge pull request #710 from johnnychen94/master
...
naive implementation of activations
2019-04-05 15:33:31 +01:00
4626f7568c
rewrite one test case
2019-04-05 18:50:15 +08:00
de7a5f4024
correct the function behavior; support Any type
2019-04-05 18:16:44 +08:00
b84ab7ac95
Removed logcosh
2019-04-05 03:16:54 +05:30
bd9d73a941
Merge #655
...
655: Added support for Float64 for DepthwiseConv r=dhairyagandhi96 a=thebhatman
DepthwiseConv was giving errors for Float64. This fixes the issue.
Co-authored-by: Manjunath Bhat <manjunathbhat9920@gmail.com>
2019-04-04 17:25:52 +00:00
261235311c
change `dims` as unbroadcasted dims and keyword argument
2019-04-05 01:19:20 +08:00
82595648e2
change 4-spaces tab to 2-spaces tab
2019-03-28 22:40:24 +08:00
13c58494ec
add x into results
2019-03-28 19:28:59 +08:00
c4ebd199db
move test cases to "basic" testset
2019-03-28 17:58:02 +08:00
47728b1899
fix test case error
2019-03-28 17:45:12 +08:00
5c2a071713
add support for 0-element Chain
2019-03-28 17:20:41 +08:00
ccfe0f8720
naive implementation of activations
2019-03-28 17:07:04 +08:00
c810fd4818
Corrected Group Size In Batch Norm Test For Group Norm
2019-03-28 01:35:38 +05:30
61c1fbd013
Made Requested Changes
2019-03-28 01:33:04 +05:30
671aed963e
Made a few fixes. Added tests
2019-03-28 00:51:50 +05:30
4efcc69ba5
logcosh averaged
2019-03-26 23:23:02 +05:30
c4d12e57fe
Loss function names in lowercase
2019-03-26 03:09:48 +05:30
f0cc4a328d
make Maxout trainable
2019-03-25 16:02:46 +00:00
ca68bf9bec
correct casing
2019-03-18 12:20:46 +00:00
e23c8ddd13
take zero-arge closure
2019-03-18 12:20:46 +00:00
fcc3ec471a
Add MaxOut layer
2019-03-18 12:19:44 +00:00
59da68b4d9
update test
2019-03-14 21:55:37 +08:00
57a52e3375
Error of recurrent decimals fixed.
2019-03-12 02:58:32 +05:30
61386c04f8
Tests added.
2019-03-12 02:36:37 +05:30
d4a1d33a31
Added Float64 tests for DepthwiseConv
2019-03-09 20:17:22 +05:30
83b4b3a714
changes based on PR comments
2019-03-07 09:46:44 +01:00
129a708b6f
instance normalization
2019-03-07 09:46:44 +01:00
9914c531f6
work around extreme slowdown due julia performance bug
2019-02-06 16:19:29 +01:00
2f3ad56166
Add test for Depthwise Conv
2019-01-24 18:53:04 +05:30
06003b72c7
noise shape for dropout
2019-01-22 23:51:38 +08:00
c74aa67c5d
fix promotion by avoiding integer division in mse and crossentropy
...
oops
add tests
2019-01-15 14:15:05 +01:00
dfd680646c
Fix conflict
2018-11-14 22:18:57 +05:30
903db70673
float32 param initialisers
2018-11-12 20:10:47 +00:00
2559e7b4e6
Fix merge conflicts
2018-10-23 21:53:29 +05:30
3bf18347e0
Fix dimensional error in test
2018-09-26 22:03:38 +08:00
b20ae0546b
rebase to pass the test
2018-09-26 20:30:13 +08:00
cc812a8f89
Fix tests
2018-09-11 17:30:54 +05:30
dd2fa77681
Fix tests
2018-09-11 17:06:18 +05:30
7e7a501efd
Fix tests
2018-09-11 16:32:14 +05:30
8bea60d980
Merge branch 'master' into cudnn_batchnorm
2018-09-11 15:34:25 +05:30
44049ce00c
Merge branch 'master' into issue-#354
2018-09-06 09:39:31 -05:00
1e90226077
actually run tests
2018-09-04 14:35:20 +01:00
1e0fd07b09
use `expand`
2018-09-04 14:30:02 +01:00
e6be639436
Merge branch 'master' into HEAD
2018-09-04 14:03:46 +01:00
b35664c59f
Update testsets
2018-08-25 16:30:46 +08:00
634d34686e
Add new constructors and test
2018-08-24 10:31:13 +08:00
4baf85bbe2
update Testset of basic.jl
2018-08-23 22:29:03 +08:00
81e5f7c991
Update test/layers/basic.jl
2018-08-23 21:59:41 +08:00
6743d52d08
Fix issue #354
2018-08-23 21:34:11 +08:00
d3c78a80be
Fix layers errors
2018-08-11 17:20:27 +05:30
3b448ce1ac
Merge branch 'master' into cudnn_batchnorm
2018-08-11 15:02:55 +05:30
0471c489e6
depwarns
2018-08-03 15:14:25 +01:00
3510c837a8
zeros replaced by zero
2018-08-03 15:14:25 +01:00
da7fe93b31
Fix test
2018-07-17 09:47:45 +05:30
646db81f94
Pull BatchNorm CPU updates
2018-07-17 09:24:38 +05:30
185e9148b6
fix cpu batchnorm
2018-07-16 07:11:33 +02:00
0e95be3326
Call Flux.Tracker.data() on ŷ for bce
2018-06-26 14:48:51 -06:00
ed032cdb1e
Change epsilon value to eps(ŷ)
2018-06-26 12:29:06 -06:00
e08fd7a6d2
Added epsilon term to binarycrossentropy
2018-06-26 11:43:16 -06:00
a4e35e9e91
Adjust atol in tests
2018-06-20 16:22:25 +05:30
5fd240f525
interface tweaks
2018-04-15 20:04:42 +01:00
07b0f95d61
Tests for batch norm with 2D and 3D convolutions.
2018-03-15 22:52:09 -04:00
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
6e65789828
Register back! for logsigmoid and implement (logit)binarycrossentropy
2018-02-06 19:32:46 +08:00
e3a688e706
use kwarg
2017-12-13 15:27:15 +00:00
128725cefd
Merge branch 'master' into sf/weighted_crossentropy
2017-12-13 15:14:47 +00:00
41446d547f
Add `weighted_crossentropy` for imbalanced classification problems
2017-12-05 17:09:05 -08:00
Mike Innes