Commit Graph

200 Commits

Author SHA1 Message Date
Kristoffer Carlsson
2298e4fea1 modernize documentation 2019-01-10 15:06:11 +01:00
Mike J Innes
f0d5624ed2
Merge pull request #493 from dhairyagandhi96/master
[WIP] New Optimiser Docs
2019-01-10 11:10:38 +00:00
Mike J Innes
81e5551256 tweaks 2019-01-10 11:01:57 +00:00
Kristoffer Carlsson
202424d1b1
Docs: fix link to CuArrays 2019-01-03 01:25:25 +01:00
Robert Hönig
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Correct the outdated Julia 0.6 requirement.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
Dhairya Gandhi
eb287ae9a0 fixed optimisers syntax 2018-12-04 16:08:03 +05:30
Dhairya Gandhi
d412845192 added training api changes 2018-12-01 16:59:27 +05:30
Dhairya Gandhi
1ea8c5a293 [WIP] add docstrings and doc improvements 2018-11-12 19:17:10 +05:30
Dhairya Gandhi
07397bc950 [WIP] add links to sgd 2018-11-12 17:53:53 +05:30
Dhairya Gandhi
4562682528 [WIP] add optimiser docs 2018-11-12 17:42:52 +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
harryscholes
61c14afee4 Add usage example of custom gradients 2018-10-09 13:05:38 +01:00
Harry
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
Harry
079614adb2
Fix typo 2018-09-19 16:45:11 +01:00
Avik Pal
eb9b408c0f
Merge branch 'master' into depthwiseconv 2018-09-15 10:21:31 +05:30
Sambit Kumar Dash
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
Mike J Innes
395a35d137 better headings 2018-09-05 17:03:41 +01:00
Mike J Innes
193c4ded19 make docs on 1.0 2018-09-05 16:52:50 +01:00
Mike J Innes
b7eaf393fc docs updates 2018-09-05 16:01:57 +01:00
Mike J Innes
41cf1f2a84
Merge pull request #381 from piever/pv/docs
fix julia 1 changes in tutorial
2018-09-04 16:00:58 +01:00
Mike J Innes
e6be639436 Merge branch 'master' into HEAD 2018-09-04 14:03:46 +01:00
Pietro Vertechi
a012d0bd51 fix vecnorm in docs 2018-08-29 23:39:43 +01:00
Pietro Vertechi
abcefb8ae3 fix foldl in tutorial 2018-08-29 18:36:24 +01:00
Yueh-Hua Tu
634d34686e Add new constructors and test 2018-08-24 10:31:13 +08:00
Mike Innes
dcde6d2217 tweaks 2018-08-23 15:44:28 +01:00
Avik Pal
a0ec472a4b
Merge branch 'master' into depthwiseconv 2018-08-08 01:20:37 +05:30
Avik Pal
4d17a1a809
Merge branch 'master' into depthwiseconv 2018-08-03 19:41:50 +05:30
Mike J Innes
70718e7a64 update treelike 2018-08-03 13:02:47 +01:00
Mike J Innes
a49e2eae41 deprecated Void 2018-08-03 12:53:52 +01:00
Yueh-Hua Tu
5b37319289 Add Maxpool and Meanpool 2018-08-01 00:10:53 +08:00
Julien Jerphanion
ee630a8566
Very Little typo. 2018-07-18 23:20:43 +02:00
Avik Pal
f57db22abe Remove unnecessary file 2018-07-13 14:27:04 +05:30
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
dda51a0140 update docs 2018-07-11 15:31:22 +01:00
Mike Innes
5d8b63dc65 avoid implementation details in docs 2018-06-29 13:53:50 +01:00
Mike J Innes
bed6d2311e clearer docs 2018-06-26 16:07:58 +01:00
Mike J Innes
d6a75e1289 add activations docs 2018-06-26 14:35:03 +01:00
Mike J Innes
4d7548b7a3 Merge commit '1490d87d8387a078a29a336cb37fd7269240179e' 2018-06-26 14:25:36 +01:00
Mike J Innes
1490d87d83 tweaks 2018-06-26 14:25:24 +01:00
Kade
aa8f79f10c Mention CUDAnative.jl's install instructions 2018-06-26 14:22:50 +01:00
Avik Pal
4a639687de Typo 2018-06-09 18:59:54 +05:30
Avik Pal
6b294736f9 Add Depthwise Convolution is Docs 2018-06-09 14:19:47 +05:30
kleskjr
dd3af0c9f7
add 'using Flux: crossentropy'
Following the suggestion from MikeInnes to use 'using Flux: crossentropy' instead 'Flux.crossentropy'
2018-06-05 14:30:14 +02:00
kleskjr
3a73902379
Solves Issue #262
Makes  the running of the basic examples smoother (Issue #262).
crossentropy is not exported by Flus so, either explicit reference or explicit export should be add to run the examples.
2018-05-25 13:54:17 +02:00
Mike Innes
5685df1691 tracker docs 2018-05-07 16:12:55 +01:00
Mike Innes
b35b27be6e doc fix 2018-05-04 15:05:02 +01:00
Iblis Lin
5faf5da171
doc: add GRU to layer reference 2018-04-18 17:36:10 +08:00
Iblis Lin
07ed439005
minor update for gpu.md code block 2018-03-19 20:03:31 +08:00
Mike Innes
eab26be0af optimiser state 2018-03-06 09:41:06 +00:00