https://github.com/JuliaDiffEq/DiffEqFlux.jl

sort by:
Revision Author Date Message Commit Date
e68e6a7 Update Project.toml 10 March 2020, 04:35:29 UTC
8f673f4 Merge pull request #181 from JuliaDiffEq/second_order support second order 10 March 2020, 02:45:23 UTC
aab1d62 fix and test 2nd order optimizers 10 March 2020, 01:55:30 UTC
b6220d9 fix Hessian calculations 09 March 2020, 22:26:57 UTC
c459ab5 support second order 09 March 2020, 19:30:50 UTC
13cb855 Merge pull request #180 from abhigupta768/progbar Add progress bar to sciml_train, fixes #158 09 March 2020, 17:26:09 UTC
35ca59b Remove message 09 March 2020, 17:25:28 UTC
1fe8040 Add Logging to Project.toml 09 March 2020, 14:33:43 UTC
d56f59a Add logmsg to enable TerminalLogger 09 March 2020, 13:51:22 UTC
b4b8053 Use TerminalLoggers for terminal progress bar 08 March 2020, 18:00:36 UTC
77f3a19 Add progress bar to sciml_train 08 March 2020, 15:36:32 UTC
bdfabd7 nlopt test dep 05 March 2020, 20:46:04 UTC
0bf6dd3 fully remove NLopt 05 March 2020, 19:49:53 UTC
aa2e1fc include some Zygote fixes 05 March 2020, 19:32:47 UTC
ef732b2 Update Project.toml 05 March 2020, 07:13:57 UTC
9bfbc1a Merge pull request #177 from abhigupta768/nlopt Setup NLopt optimizers with sciml_train 05 March 2020, 07:00:27 UTC
8f6250e Update src/DiffEqFlux.jl 04 March 2020, 22:26:38 UTC
405b2a5 Return MultivariateOptimizationResults object with nlopt 04 March 2020, 22:02:29 UTC
5c16710 Move sciml_train to new file 04 March 2020, 21:37:11 UTC
d8efda8 Use import for NLopt 04 March 2020, 14:17:39 UTC
d908069 Add maxeval kwarg and bounded optimization dispatch 04 March 2020, 14:14:46 UTC
f6fb6ee Setup NLopt optimizers with sciml_train Fixes #161 04 March 2020, 10:12:24 UTC
a0b09fa Update Project.toml 04 March 2020, 07:05:07 UTC
38b04ce Merge pull request #176 from JuliaDiffEq/training Alternative training AD modes 04 March 2020, 06:53:48 UTC
b7d92dd nicer test results 04 March 2020, 06:24:29 UTC
19aa435 fix delay in test 04 March 2020, 05:57:44 UTC
10c925e even simpler tests 04 March 2020, 05:31:23 UTC
73c3205 test chagnges 04 March 2020, 05:17:57 UTC
5098d01 update neural ODE training time 04 March 2020, 04:57:59 UTC
3ef2c63 add ReverseDiff 04 March 2020, 04:55:06 UTC
aef3333 minor bump 04 March 2020, 04:34:56 UTC
b2ede4a alternative training modes to be left undocumented: a backdoor to try other ADs 04 March 2020, 04:34:37 UTC
164aa78 Update Project.toml 03 March 2020, 19:21:59 UTC
ed3ec4b Merge pull request #175 from JuliaDiffEq/forward Allow ForwardDiff inside of sciml_train calls 03 March 2020, 19:21:15 UTC
473e5ff ForwardDiff-aware training 03 March 2020, 16:46:55 UTC
84793ec Merge branch 'neuraldae' 03 March 2020, 16:46:28 UTC
219a41d add to README 03 March 2020, 16:46:21 UTC
96987c4 compile the ReverseDiff VJP 03 March 2020, 15:52:51 UTC
436fa68 finish up and test NeuralODEMM 03 March 2020, 15:33:00 UTC
c8caad9 Update MWE script 02 March 2020, 17:02:50 UTC
9270f12 Separate differentiable_vars and mass_matrix DAEs and update MWE to mass_matrix 02 March 2020, 15:08:56 UTC
48ec240 Add initial version of mass_matrix neuraldae 01 March 2020, 04:06:16 UTC
25c7d57 Merge pull request #172 from JuliaDiffEq/ChrisRackauckas-patch-2 Fix loss in callback to be computed before updating parameters 28 February 2020, 00:35:34 UTC
b808bfa Fix loss in callback to be computed before updating parameters Fixes https://github.com/JuliaDiffEq/DiffEqFlux.jl/issues/166#issuecomment-590476701 24 February 2020, 18:26:37 UTC
997e553 Add desired MWE Script 23 February 2020, 18:40:38 UTC
7c90a6a Some updates to NeuralDAE constructor 23 February 2020, 18:34:38 UTC
5a261cd Add NeuralDAE struct and constructor 23 February 2020, 18:34:38 UTC
19af8e5 Update Project.toml 19 February 2020, 14:06:23 UTC
397346e Merge pull request #165 from JuliaDiffEq/data Fix data splat in Flux optimizer version of sciml_train 19 February 2020, 14:02:22 UTC
28c9345 iterate after the callback 19 February 2020, 13:38:27 UTC
422d2c1 Iterate optim batches in the callback 19 February 2020, 13:29:40 UTC
96ad21d simpler test 19 February 2020, 06:38:48 UTC
5125be7 quicker test 19 February 2020, 06:17:41 UTC
c7bcdc7 Fix data splat in Flux optimizer version of sciml_train 19 February 2020, 00:52:25 UTC
68c5571 Merge pull request #163 from JuliaDiffEq/optional_data Add an optional data argument and fix docstring 18 February 2020, 14:31:20 UTC
1c67e1e fix up null iterator 18 February 2020, 05:32:58 UTC
e1cbfd3 Add an optional data argument 18 February 2020, 04:52:56 UTC
cfe6204 Merge pull request #157 from JuliaDiffEq/compathelper/new_version/2020-02-16-11-08-34-318-1059532658 CompatHelper: bump compat for "Juno" to "0.8" 16 February 2020, 13:41:09 UTC
c2dd815 CompatHelper: bump compat for "Juno" to "0.8" 16 February 2020, 11:08:35 UTC
b5fbebf Update README.md 13 February 2020, 14:33:23 UTC
c7c5a63 Merge pull request #151 from abhigupta768/boxConstrainedOptim [WIP] Add box constrained optimization dispatch in sciml_train 11 February 2020, 13:25:45 UTC
8c2fa0b Move bounds to kwargs 11 February 2020, 07:09:35 UTC
4be8273 add box constrained optimization 10 February 2020, 19:16:55 UTC
06cf220 Merge pull request #147 from ali-ramadhan/ar/readme-toc Add table of contents to README 09 February 2020, 23:07:22 UTC
6952bbf Add table of contents to README 09 February 2020, 22:58:28 UTC
052134b Merge pull request #145 from JuliaTagBot/master Install TagBot as a GitHub Action 08 February 2020, 15:38:14 UTC
a72fdc2 Install TagBot as a GitHub Action 08 February 2020, 12:57:20 UTC
7df25ac Update .gitlab-ci.yml 08 February 2020, 07:40:37 UTC
b853636 add some usings 08 February 2020, 04:51:58 UTC
38256f1 Update Project.toml 07 February 2020, 22:55:02 UTC
ece159d Merge pull request #141 from JuliaDiffEq/fast_adjoints fast adjoints for fast layers 07 February 2020, 22:54:23 UTC
8167068 fix typo 07 February 2020, 19:52:55 UTC
fcc7454 specialize tanh derivative 07 February 2020, 19:32:15 UTC
e21b9d1 fully remove unsafe arrays 07 February 2020, 17:32:29 UTC
66fc811 Remove UnsafeArrays 07 February 2020, 17:23:54 UTC
e723541 mark fixed test 07 February 2020, 14:08:08 UTC
86e8bc3 fix test with using 07 February 2020, 13:22:51 UTC
19753d9 Make nonlinear optimal control use fast layers 07 February 2020, 05:30:17 UTC
25c97af make README example a little nicer 07 February 2020, 05:13:24 UTC
f903360 fast adjoints for fast layers Pulls about another 2x acceleration out. ```julia using DiffEqFlux fd = FastDense(2,25,tanh) pd = initial_params(fd) fs = StaticDense(2,25,tanh) x = rand(2) using BenchmarkTools @btime Flux.Zygote.gradient((x,p)->sum(fd(x,p)),x,pd) @btime Flux.Zygote.gradient((x,p)->sum(fs(x,p)),x,pd) # FastDense before: 7.900 μs (100 allocations: 7.69 KiB) 8.066 μs (100 allocations: 7.69 KiB) # FastDense after: 5.283 μs (38 allocations: 3.98 KiB) 5.267 μs (38 allocations: 3.98 KiB) # StaticDense 5.000 μs (25 allocations: 2.73 KiB) 5.067 μs (25 allocations: 2.73 KiB) ``` 07 February 2020, 04:59:50 UTC
9ea5d67 Merge pull request #137 from JuliaDiffEq/gpu fix a bunch of GPU tests 06 February 2020, 21:57:21 UTC
9c366c8 comment broken tests 06 February 2020, 21:23:36 UTC
0d4fab6 fix a bunch of GPU tests 06 February 2020, 21:23:06 UTC
364ea75 Update Project.toml 06 February 2020, 20:46:20 UTC
8fd8a4f fix SDE for sciml_train 06 February 2020, 19:09:09 UTC
448cc00 Merge pull request #139 from ric-cioffi/patch-1 stopping criterion on current loss 06 February 2020, 18:36:09 UTC
498aa89 fix Optim setup 06 February 2020, 15:55:12 UTC
52f13be sciml_train! -> sciml_train and boolean for halting in a safe way 06 February 2020, 14:09:19 UTC
d0017f9 Update appveyor.yml 05 February 2020, 23:44:31 UTC
0d51a5e stopping criterion on current loss We can make this directly depend on the callback function (which is consistent with Optim). For example a reasonable callback function would be function cb(θ, l) println("Current loss: ", l) return l < 1e-4 end 05 February 2020, 22:37:30 UTC
6331437 Update Project.toml 04 February 2020, 20:34:25 UTC
fb58ee4 Merge pull request #136 from JuliaDiffEq/abstract add some abstract types 04 February 2020, 20:34:09 UTC
b261c3a Update fast_layers.jl 04 February 2020, 19:53:24 UTC
0a0d436 add some abstract types 04 February 2020, 19:09:23 UTC
49a0f9d patch version 02 February 2020, 22:37:39 UTC
2623712 Merge remote-tracking branch 'origin/master' 02 February 2020, 22:37:25 UTC
9e650d3 add missing paramlength 02 February 2020, 22:37:20 UTC
bb0a9f4 Update Project.toml 02 February 2020, 20:22:30 UTC
9503182 Update Project.toml 02 February 2020, 19:11:33 UTC
ffa8de3 Merge pull request #131 from JuliaDiffEq/compathelper/new_version/2020-02-02-19-06-06-079-2925281732 CompatHelper: add new compat entry for "UnsafeArrays" at version "1.0" 02 February 2020, 19:11:12 UTC
back to top