Commit Graph

544 Commits

Author SHA1 Message Date
Adarsh Kumar
5565250c28
Updated test for tversky 2020-03-02 13:46:33 +05:30
Adarsh Kumar
57c1b67d08
Merge branch 'master' into patch-1 2020-03-01 11:49:33 +05:30
CarloLucibello
a1efc434c2 fix typo 2020-02-29 19:40:44 +01:00
CarloLucibello
b6c79b38b4 add DataLoader
special case train! for the unsupervised data iterator
2020-02-29 18:50:59 +01:00
bors[bot]
37af9fb15c
Merge #1023
1023: Feature: Added Boston Housing Dataset r=CarloLucibello a=pranjaldatta

[Boston Housing Dataset](https://archive.ics.uci.edu/ml/machine-learning-databases/housing/) is one of the most common datasets that are used by beginners. It is as popular as other datasets like Iris etc. Hence, it feels only natural that this dataset is a part of Flux.

Added src/data/housing.jl: code for downloading and loading the dataset
Edited src/data/Data.jl: To include and export housing.jl
Edited test/data.jl: Added test for the dataset.

*All tests in test/data.jl are passing*

Co-authored-by: pranjaldatta <pranjaldatta99@gmail.com>
Co-authored-by: Pranjal  Datta <pranjaldatta99@gmail.com>
2020-02-29 15:54:34 +00:00
bors[bot]
2dd23574c0
Merge #998
998: test restructure on the GPU r=CarloLucibello a=ChrisRackauckas

Requires https://github.com/FluxML/Zygote.jl/pull/474 to pass

Co-authored-by: Chris Rackauckas <accounts@chrisrackauckas.com>
2020-02-29 09:08:11 +00:00
Adarsh Kumar
8afed01345
Apply suggestions from code review
Co-Authored-By: David Lung <lungd@users.noreply.github.com>
2020-02-27 23:23:53 +05:30
Adarsh Kumar
3d8965230f
Added tests for dice and Tversky loss 2020-02-27 02:29:39 +05:30
pranjaldatta
569021a9f1 added newlines at end of file 2020-02-26 15:05:23 +05:30
bors[bot]
55616afc11
Merge #960
960: Added utility function outdims to compute output dimensions of a layer r=dhairyagandhi96 a=darsnack

Based on Slack chatter, I added a utility function, `outdims`, that computes the output dimensions for given input dimensions.

Example
```julia
layer = Conv((3, 3), 3 => 16)
outdims(layer, (10, 10)) # returns (8, 8)
```

Co-authored-by: Kyle Daruwalla <daruwalla@wisc.edu>
2020-02-25 17:40:05 +00:00
pranjaldatta
197a1a70c0 added BostonHousing dataset and testing 2020-02-07 03:47:19 +05:30
Adarsh Kumar
659ba074d1
Updated test for msle 2020-02-06 01:21:51 +05:30
Adarsh Kumar
44a977b7a4
Added tests for new loss functions 2020-02-05 23:20:06 +05:30
Tim Besard
e2c2ec5575 Don't invoke GPU crossentropy with integers.
Broadcasting log on integers does not work.
2020-01-31 08:22:54 +01:00
Tim Besard
e66a7f130f Don't compare CPU with GPU arrays. 2020-01-31 08:22:21 +01:00
Chris Rackauckas
9803826a36 test restructure on the GPU
Requires https://github.com/FluxML/Zygote.jl/pull/474
2020-01-20 13:53:28 -05:00
bors[bot]
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
Manjunath Bhat
747e01ea02
Test to check for spurious promotions 2020-01-13 18:33:30 +05:30
Elliot Saba
0fdcc00923 Give NNPACK a bit of numerical leeway 2019-12-23 01:31:26 -08:00
Kyle Daruwalla
0cdd11c0dc Added tests for varying padding, stride, and dilation with outdims. 2019-12-07 14:05:50 -06:00
Kyle Daruwalla
6265b1fa39 Added tests for outdims 2019-12-05 22:54:25 -06:00
bors[bot]
90a38a3201
Merge #937
937: Fix Glorot initialization, add He initialization r=MikeInnes a=Sleort

Should fix #442 .
Adds He weight initialization as a bonus :-)

Co-authored-by: Troels Arnfred Bojesen <tr-ab@online.no>
2019-11-26 16:17:06 +00:00
bors[bot]
fb4a48f970
Merge #943
943: Fixes #900 r=MikeInnes a=dhairyagandhi96

Thoughts on the test?

cc @MikeInnes

Co-authored-by: Dhairya Gandhi <dhairya@juliacopmuting.com>
2019-11-26 15:09:27 +00:00
Dhairya Gandhi
c031ae1a94 correct channel value 2019-11-24 13:31:31 +05:30
Dhairya Gandhi
5f21238d1a no grad dims helper 2019-11-24 13:25:02 +05:30
matsueushi
a0314ce682 Fix logitbinarycrossentropy on CuArrays 2019-11-22 05:23:24 +00:00
Troels Arnfred Bojesen
af96a197c1 Fix Glorot initialization
Should fix #442
2019-11-20 13:20:42 +09:00
Troels Arnfred Bojesen
2b80573248 Fix Glorot initialization, add He initialization
Should fix #442 .
Adds He weight initialization as a bonus :-)
2019-11-19 18:16:29 +09:00
Troels Arnfred Bojesen
4530ac65c7 Fix Glorot initialization, add He initialization
Should fix the issue reported at https://github.com/FluxML/Flux.jl/issues/442 .
Adds He weight initialization as a bonus :-)
2019-11-19 16:50:40 +09:00
dsweber2
dea29532ef Merge branch 'master' into activations 2019-11-15 17:19:43 -08:00
bors[bot]
7eb6a0c98c
Merge #932
932: Travis: test on 1.0 r=MikeInnes a=MikeInnes



Co-authored-by: Mike J Innes <mike.j.innes@gmail.com>
Co-authored-by: Mike Innes <mike.j.innes@gmail.com>
2019-11-15 16:21:30 +00:00
Mike Innes
e24215ca98 guard test on 1.0 2019-11-15 15:59:42 +00:00
dsweber2
58c794702d simpler test 2019-11-14 14:05:53 -08:00
dsweber2
db92b0e3ce super simple test 2019-11-14 13:40:52 -08:00
janEbert
a00d8d94ec Add test for CUDA binarycrossentropy 2019-11-08 17:28:54 +01:00
Tim Besard
33d276cdb7 Fix GPU-less tests. 2019-11-04 15:51:33 +01:00
Tim Besard
39ab740fb7 Check for CUDA availability at run time. 2019-11-02 11:18:06 +01:00
Katharine Hyatt
8913c9c741 Make the vector of weights test pass on GPU 2019-10-23 09:53:09 -04:00
Katharine Hyatt
f7ce717aaa Add tests 2019-10-23 09:22:22 -04:00
Manjunath Bhat
2b30319a55
Merge branch 'master' into patch-6 2019-09-30 21:05:02 +05:30
thebhatman
6e289ef939 Merge branch 'patch-6' of https://github.com/thebhatman/Flux.jl into patch-6 2019-09-30 20:55:44 +05:30
Mike Innes
b90b02872f Merge branch 'master' into tb/cuarrays_dnn 2019-09-27 14:58:32 +01:00
Mike Innes
691a29cf32 cudnn bug is fixed 2019-09-27 14:15:58 +01:00
bors[bot]
acb6a89245
Merge #865
865: Functor r=MikeInnes a=MikeInnes

This refactors our current `@treelike` infrastructure. It somewhat formalises what we're doing around the idea of a Flux model as a functor, i.e. something that can be mapped over.

This is much more flexible than what we had before, and avoids some issues. It allows layers to have state that isn't mappable; it allows for dispatch when walking the tree, which means layers like `BatchNorm` can have non-trainable parameters; and it also allows for zipped mapping like `fmap(+, xs, ys)`, which isn't implemented yet but will be useful for the new optimisers work.

The main downside is that the term `functor` has been previously used in the Julia community as a malapropism for "thing that behaves like a function"; but hopefully this can start to reduce that usage.

Co-authored-by: Mike Innes <mike.j.innes@gmail.com>
2019-09-24 16:36:10 +00:00
Dhairya Gandhi
822288d63d merge conflicts 2019-09-24 00:31:44 +05:30
Mike Innes
b60df53ba1 pkg up 2019-09-19 18:33:33 +01:00
Mike Innes
cabb81e30b internal rename 2019-09-19 15:53:31 +01:00
Mike Innes
b951377426 fix normalisation layer params 2019-09-19 15:33:24 +01:00
Mike Innes
f8d5d3b5fc broken normalisation layer params 2019-09-19 14:12:11 +01:00
Mike Innes
c5e56b7e04 move setweights and copy_transpose 2019-09-17 17:22:35 +01:00