37d58e16dd
common questions answered in docs
2020-02-08 16:33:18 +05:30
7797e31b44
Add custom training loops to docs
2020-01-16 21:57:59 +00:00
d1edd9b16d
Merge #680
...
680: Added new loss functions. r=thebhatman a=thebhatman
I have added the KL Divergence Loss function, Poisson loss function, Logcosh loss, and Hinge loss function.
Co-authored-by: Manjunath Bhat <manjunathbhat9920@gmail.com>
Co-authored-by: thebhatman <manjunathbhat9920@gmail.com>
2020-01-13 15:46:25 +00:00
8a93be8c6c
Change loss to cost
2019-12-09 20:39:46 +05:30
04991d3261
Added entry to docs for outdims
2019-12-07 14:06:11 -06:00
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
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
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
776023ddad
fixes
2019-10-10 20:35:28 +05:30
4477dd8d54
reviews
2019-10-10 20:27:11 +05:30
a55878453c
typo
...
Co-Authored-By: Mike J Innes <mike.j.innes@gmail.com>
2019-10-10 20:16:29 +05:30
623ee2c29c
typo
...
Co-Authored-By: Mike J Innes <mike.j.innes@gmail.com>
2019-10-10 20:16:00 +05:30
d591b2b59e
Removed colon and capitalised
2019-10-09 21:36:40 +05:30
96a23c295c
Changes to docs
2019-10-09 14:53:03 +05:30
2b30319a55
Merge branch 'master' into patch-6
2019-09-30 21:05:02 +05:30
ec35e9cbaa
Loss functions docs added in layers.md
2019-09-30 21:02:13 +05:30
6e289ef939
Merge branch 'patch-6' of https://github.com/thebhatman/Flux.jl into patch-6
2019-09-30 20:55:44 +05:30
32ac71734d
optimiser interface docs
2019-09-27 21:43:59 +05:30
a98a1b8bb5
fixes
2019-09-27 21:43:39 +05:30
cabb81e30b
internal rename
2019-09-19 15:53:31 +01:00
a600a9ceed
removed extra parenthesis
2019-09-14 10:56:17 +05:30
e0276139e1
Update docs/src/training/optimisers.md
...
Co-Authored-By: Mike J Innes <mike.j.innes@gmail.com>
2019-09-11 19:21:15 +05:30
b6926f07a5
cleanup
2019-09-11 19:18:50 +05:30
b08c949b99
fixes to saving
2019-09-11 14:25:46 +05:30
a9d1cbf07c
added decays
2019-09-10 21:20:05 +05:30
b6c8312796
optimiser docs
2019-09-10 20:49:15 +05:30
de2049450b
docs mostly fixed
2019-09-10 15:17:07 +01:00
ddf06af0b9
remove tracker docs
2019-09-10 15:03:08 +01:00
c8d460ff84
doctests passing
2019-09-10 15:02:43 +01:00
67c38b3099
Merge branch 'master' into zygote
2019-09-06 15:18:58 +01:00
62ec01a6f5
doc build changes
2019-08-19 15:49:50 +01:00
bab618d168
Merge pull request #767 from oxinabox/patch-6
...
Some cleanup on performance tips docs
2019-07-11 16:11:44 +01:00
27904d349c
Update performance.md
2019-07-11 16:11:32 +01:00
b24e05bb20
Fix lack of x
2019-07-02 13:15:54 -04:00
e17999f19b
Two minor typos
2019-06-11 22:09:59 -07:00
b98075817c
Merge branch 'master' into DenseBlock
2019-06-05 14:27:47 +01:00
fe759ac43c
Update docs/src/performance.md
...
Co-Authored-By: Kristoffer Carlsson <kristoffer.carlsson@chalmers.se>
2019-05-28 14:19:56 +01:00
f263f0c8ed
add to layer docs
2019-05-14 02:53:06 -07:00
6b3cd825b9
Added SkipConnection to docs tentatively in Other General Purporse Layers
2019-05-13 16:43:14 -03:00
7103a61a1f
delete redundant section
2019-05-11 12:40:01 +08:00
fc4827c48f
Some cleanup on performance tips
2019-05-07 16:38:21 +01:00
c9148194cf
Update `docs/` Manifest
2019-04-25 10:22:29 -07:00
77e3ff7a8c
fixed docs
2019-04-24 21:16:31 +05:30
1eca23e113
Merge branch 'master' of https://github.com/FluxML/Flux.jl
2019-04-20 11:26:24 +02:00
934f7f932d
Updated docs again.
2019-04-20 11:22:48 +02:00
710084ffbf
Loss functions added to docs
2019-04-05 23:50:16 +05:30
2a6eb35a71
Added GroupNorm to docs and News.md
2019-04-05 23:16:46 +05:30
cad2df2c41
add other optimizers to documentation
2019-04-05 01:25:21 +04:30
a5c34e8325
Fixed merging with upstream Flux.
2019-03-27 20:30:31 +01:00
d68866a238
Fixed documentation error.
2019-03-27 20:22:01 +01:00
ab46da11c7
Merge pull request #685 from jpsamaroo/jps/recur-docs-reset
...
Add note on reset! usage in recurrence docs
2019-03-27 12:47:01 +00:00
1930f40dec
Add note on reset! usage in recurrence docs
2019-03-26 00:00:00 -05:00
eeed8b24c3
Merge pull request #681 from dellison/stopdoc
...
add Flux.stop to training docs
2019-03-25 15:07:07 +00:00
025d9b678d
Update docs/src/models/layers.md
...
Co-Authored-By: oxinabox <oxinabox@ucc.asn.au>
2019-03-18 12:20:46 +00:00
2bc4b8d1a4
Update docs/src/models/layers.md
...
Co-Authored-By: oxinabox <oxinabox@ucc.asn.au>
2019-03-18 12:20:46 +00:00
c76b9c7e2c
fix docs
2019-03-18 12:20:46 +00:00
838047f708
fix docs
2019-03-18 12:19:44 +00:00
c1a33c556f
do things to docs
2019-03-18 12:19:44 +00:00
263a3248f6
add Flux.stop to training docs
2019-03-11 19:52:05 -07:00
b348e31f07
Merge pull request #667 from FluxML/donottrack
...
rm Tracker
2019-03-08 11:38:37 +00:00
194e2ecd50
update docs manifest
2019-03-08 11:20:39 +00:00
922e9c9bc2
Updated docs with AlphaDropout
2019-03-04 01:10:12 +05:30
ebf50f4e1c
Create performance tips docs section ( #615 )
...
* Create performance_tips.jl
* Rename performance_tips.jl to performance_tips.md
* add perf tips
* Update docs/src/performance_tips.md
Co-Authored-By: oxinabox <oxinabox@ucc.asn.au>
* Update docs/src/performance_tips.md
Co-Authored-By: oxinabox <oxinabox@ucc.asn.au>
* Update make.jl
* Update and rename performance_tips.md to performance.md
* spelling
* Update docs/src/performance.md
Co-Authored-By: oxinabox <oxinabox@ucc.asn.au>
* Update docs/src/performance.md
Co-Authored-By: oxinabox <oxinabox@ucc.asn.au>
* Update performance.md
* Update performance.md
* Update docs/src/performance.md
Co-Authored-By: oxinabox <oxinabox@ucc.asn.au>
* Update docs/src/performance.md
Co-Authored-By: oxinabox <oxinabox@ucc.asn.au>
2019-02-19 15:03:41 +00:00
08b87e0bce
Transition to doctests ( #616 )
...
* basics.md: Initial doctest to an example
Related to https://github.com/FluxML/Flux.jl/issues/561
* make.jl: Allow doctest to run
* Fix comments in order to pass doctests
* basic.md: Add doctests to examples
2019-02-14 18:29:27 +00:00
c093d089a6
Add conv_transpose to docs
2019-02-06 21:11:41 +05:30
8386a49bf9
Merge pull request #575 from FluxML/mji/update
...
Clean up parameter update API
2019-01-28 15:26:57 +00:00
e1cac76a34
params update
2019-01-28 14:14:41 +00:00
0f8a4a48c6
extend update! with an optimiser
2019-01-28 14:10:09 +00:00
bb2210f552
Merge pull request #553 from xiaodaigh/patch-2
...
Updated with more detailed instructions for installing CuArrays
2019-01-28 10:36:27 +00:00
5930ac1730
simplified instructions
2019-01-26 12:26:48 +11:00
3cc3c463a3
Adding `nest = true` option in `Tracker.gradient`
...
otherwise fails and returns an error. Note that option has to be added in both `df` and `d2f`.
2019-01-24 19:29:29 -05:00
bc68dfbd75
docs/basics.md: Add `using Flux`
...
In order to import sigmoid function.
2019-01-23 19:20:10 +05:30
236b103b73
docs/basics.md: Add `tracked` after 1.0
2019-01-22 23:37:34 +05:30
3f62bc30b9
Update gpu.md
2019-01-11 15:57:54 +11:00
e13c6c1125
updated gpu.md with installation instructions
2019-01-11 15:55:39 +11:00
2298e4fea1
modernize documentation
2019-01-10 15:06:11 +01:00
f0d5624ed2
Merge pull request #493 from dhairyagandhi96/master
...
[WIP] New Optimiser Docs
2019-01-10 11:10:38 +00:00
81e5551256
tweaks
2019-01-10 11:01:57 +00:00
202424d1b1
Docs: fix link to CuArrays
2019-01-03 01:25:25 +01:00
0f243dba29
Correct CuArrays requirements.
...
According to the CuArrays README, "CuArrays should work out-of-the-box on Julia 1.0."
Correct the outdated Julia 0.6 requirement. Also, update the instructions link to point to the
CuArrays.jl README, which has setup instructions (CUDAnative.jl's README doesn't).
2018-12-19 09:23:26 +01:00
eb287ae9a0
fixed optimisers syntax
2018-12-04 16:08:03 +05:30
d412845192
added training api changes
2018-12-01 16:59:27 +05:30
1ea8c5a293
[WIP] add docstrings and doc improvements
2018-11-12 19:17:10 +05:30
07397bc950
[WIP] add links to sgd
2018-11-12 17:53:53 +05:30
4562682528
[WIP] add optimiser docs
2018-11-12 17:42:52 +05:30
bbccdb3eec
Merge pull request #279 from avik-pal/depthwiseconv
...
Adds support for Depthwise Convolutions
2018-10-23 17:22:15 +01:00
61c14afee4
Add usage example of custom gradients
2018-10-09 13:05:38 +01:00
179a1e8407
Correct Custom Gradients docs
...
* Fixed a type signature that was incorrect.
* Also, replaced `data(a)` with `a.data`. Don't know if the syntax has changed (recently). This may also need to be corrected in line 121.
MWE:
```julia
using Flux
using Flux.Tracker
using Flux.Tracker: forward, TrackedReal, track, @grad
minus(a, b) = a - b
minus(a::TrackedReal, b::TrackedReal) = Tracker.track(minus, a, b)
@grad function minus(a, b)
return minus(a.data, b.data), Δ -> (Δ, -Δ)
end
a, b = param(2), param(4)
c = minus(a, b) # -2.0 (tracked)
Tracker.back!(c)
Tracker.grad(a) # 1.00
Tracker.grad(b) # -1.00
```
2018-09-21 16:57:54 +01:00
079614adb2
Fix typo
2018-09-19 16:45:11 +01:00
eb9b408c0f
Merge branch 'master' into depthwiseconv
2018-09-15 10:21:31 +05:30
8b9a98ed01
The sample gradient should not use the softdash
...
While softdash is a very natural and mathematical way of representation, it can be very easily confused with the apostrophe used for LinAlg adjoint. Not worth and unnecessary confusion in a first example of the code.
2018-09-11 18:58:07 +05:30
395a35d137
better headings
2018-09-05 17:03:41 +01:00
193c4ded19
make docs on 1.0
2018-09-05 16:52:50 +01:00
b7eaf393fc
docs updates
2018-09-05 16:01:57 +01:00
41cf1f2a84
Merge pull request #381 from piever/pv/docs
...
fix julia 1 changes in tutorial
2018-09-04 16:00:58 +01:00
e6be639436
Merge branch 'master' into HEAD
2018-09-04 14:03:46 +01:00
a012d0bd51
fix vecnorm in docs
2018-08-29 23:39:43 +01:00
abcefb8ae3
fix foldl in tutorial
2018-08-29 18:36:24 +01:00
634d34686e
Add new constructors and test
2018-08-24 10:31:13 +08:00
Dhairya Gandhi