HuwCampbell/grenade
1
1
Fork 0
mirror of https://github.com/HuwCampbell/grenade.git synced 2024-11-23 09:22:11 +03:00
Code Issues Projects Releases Wiki Activity
86 Commits 5 Branches 1 Tag 13 MiB
c2d48a368c
Commit Graph

86 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Huw Campbell
c2d48a368c Add tests for Pad and Crop layers 2017-02-03 23:56:47 +11:00
Huw Campbell
df9f80a9cf Update Readme with new network type 2017-02-03 22:47:28 +11:00
Huw Campbell
c8cfa399e7 Split back propagation function into two. 
We now have one function which gives a Tape and
the output, and another which takes the Tape and
a loss gradient.

This has a great benefit, in that people can build
their own losses, which makes things like GANs
really easy.
 2017-02-03 22:44:31 +11:00
Huw Campbell
7d476bf0f6 Semigroup dep for optparse 2017-02-03 21:18:53 +11:00
Huw Campbell
1e461cb07a Make Pad 3D faster. 
Using dependent types in the deeper functions and
requiring a Proxy to reach them meant we required
dictionary passing to get the Nats. This made the
pad and crop layers almost 1000 times slower than
they should have been.
 2017-02-03 21:05:14 +11:00
Huw Campbell
dbeb962ae6 Fix many warnings 2017-02-03 14:43:07 +11:00
Huw Campbell
7af621cbb6 Add c 3d pad and crop functions 2017-02-02 20:27:02 +11:00
Huw Campbell
a23103ee7b Add extra composition 2017-02-01 22:13:20 +11:00
Huw Campbell
32f3e317e8 Change fusing layers so we can have two paths of sub networks 2017-02-01 14:17:18 +11:00
Huw Campbell
e6179ce5a4 Add recurrent tapes 2017-01-28 14:13:00 +11:00
Huw Campbell
d82a121797 Remove Show constraint on UpdateLayer 2017-01-24 13:47:47 +11:00
Huw Campbell
148c7778ab Simplify Network Type 2017-01-23 12:47:10 +11:00
Huw Campbell
6ad9803286 Start working on Tape 2017-01-21 12:46:40 +11:00
Huw Campbell
51ae147306 Add benchmark file 2017-01-20 18:53:18 +11:00
Huw Campbell
16573158d8 Nicer type 2017-01-19 23:08:01 +11:00
Huw Campbell
9989092216 Update Readme 2017-01-19 20:52:22 +11:00
Huw Campbell
df75beee8d Missing test file 2017-01-19 19:49:13 +11:00
Huw Campbell
2369ec3407 Merge pull request #15 from HuwCampbell/topic/cereal 
Add very basic model saving and loading
 2017-01-19 19:06:36 +11:00
Huw Campbell
7c4916409d Add command line parameters for shakespeare example 2017-01-19 19:04:15 +11:00
Huw Campbell
bcd1856988 Update LSTM 2017-01-19 18:56:22 +11:00
Huw Campbell
48263cd9e2 Update README.md 
Add recurrent
 2017-01-17 19:47:39 +11:00
Huw Campbell
4dc408f39d Add very basic model saving and loading 2017-01-16 10:16:40 +11:00
Huw Campbell
20e7e483d7 Fix 7.10 builds 2017-01-16 00:29:25 +11:00
Huw Campbell
cc70f1fc0c Merge pull request #18 from HuwCampbell/topic/recurrent 
Recurrent nets and other changes
 2017-01-14 21:16:48 +11:00
Huw Campbell
ac0e4b22c8 Remove primes on shape instantiations 
Add singletons for Shape and remove hacks on recurrent nets

Add Recurrent Nets
 2017-01-14 21:09:07 +11:00
Huw Campbell
88021fbde7 Better testing 2016-12-15 20:04:45 +11:00
Huw Campbell
424d791a30 Fix silent conversion bug in pooling layer 
Add quickcheck against reference implemenations for layer internals

Add skolem layer generators.
 2016-12-15 11:21:37 +11:00
Huw Campbell
70e9b83b04 Remove unneeded function 2016-12-13 11:09:35 +11:00
Huw Campbell
fc958630c4 Merge pull request #16 from HuwCampbell/topic/performance 
Topic/performance
 2016-12-13 11:01:35 +11:00
Huw Campbell
bacfa8145b Update REAMDE and use type synonyms 2016-12-13 10:59:29 +11:00
Huw Campbell
9df47d5c7e Remove indexed Vector type 2016-12-13 09:51:55 +11:00
Huw Campbell
6417151620 Make Grenade fast 
Changes shapes to get rid of the Vector, all data is
now held in contiguous memory.

Add fast c implementations for pooling layers.

Now does mnist on my laptop in 12 minutes.
 2016-12-13 08:39:32 +11:00
Huw Campbell
1ec65a414f Add stupidly fast col2im 2016-12-13 01:11:18 +11:00
Huw Campbell
3830e55a7c Add stupidly fast im2col in c 2016-12-12 23:35:00 +11:00
Huw Campbell
f04bfebfee Speed up im2col, vid2col. 
Each point on the output is written to precisely once, so we don't
need to initialise it or use an additive update modifier.
 2016-12-12 12:59:41 +11:00
Huw Campbell
bd881faf2b Add some benchmarks 2016-12-12 10:20:40 +11:00
Huw Campbell
c0bb69de3b Update README 2016-12-09 22:48:41 +11:00
Huw Campbell
2cffa4a568 Merge pull request #14 from HuwCampbell/topic/performance 
Topic/performance
 2016-12-09 22:04:50 +11:00
Huw Campbell
267ebc2080 Optimise poolForwardFit 2016-12-09 22:03:29 +11:00
Huw Campbell
b914b91c1f Reimplement pooling backwards for speed 2016-12-09 22:03:29 +11:00
Huw Campbell
bbd29e71bd Make ST modifications strict 2016-12-09 22:03:29 +11:00
Huw Campbell
8b3ca1e0b6 Merge pull request #13 from HuwCampbell/topic/performance 
Topic/performance
 2016-12-09 10:44:51 +11:00
Huw Campbell
a29afe8603 Replace dodgy sequence 2016-12-09 09:17:23 +11:00
Huw Campbell
eb179d071b Add another test 2016-12-08 21:11:50 +11:00
Huw Campbell
24289dba41 Add faster maxIndex and maxElement for matrices 2016-12-08 21:07:18 +11:00
Huw Campbell
ff20855676 Minor changes 2016-12-08 10:32:07 +11:00
Huw Campbell
2433e1fba2 Remove old functions 2016-12-08 10:10:14 +11:00
Huw Campbell
670f2d952f Tests 2016-12-08 10:10:14 +11:00
Huw Campbell
b090b5f073 Make things faster 2016-12-08 10:10:14 +11:00
Huw Campbell
d360438fc0 Update hmatrix 2016-12-08 10:10:13 +11:00