Commit graph

201 commits

Author SHA1 Message Date
7d709c0fa5 Bugfix: Fix crashes in DatasetFetcher 2019-07-30 15:15:34 +01:00
8917f746ec Add todo 2019-07-29 18:07:17 +01:00
03c1cbb97f Finish refactoring to use Brain.js, but it's untested. 2019-07-29 18:06:50 +01:00
cce0761fed Continue brain.js refactoring, but it's still not finished yet. 2019-07-29 17:02:34 +01:00
2a81ac792e Start replacing Tensorflow with Brain.js, but it's not finished yet
Note to self: bug them to upgrade ot GPU.js 2 for future projects
2019-07-29 14:36:52 +01:00
b2efeae563 Remove Tensorflow.js dependency 2019-07-29 14:17:47 +01:00
43f99d6b5d Try to add an additional input to the neural network, but it's not working. 2019-07-29 14:17:28 +01:00
9e93940225 Log the statistics to the console 2019-07-26 15:26:10 +01:00
048a5c25a7 Add loading animation 2019-07-26 15:05:16 +01:00
f8b09e5b9d Add gateway marker layer to display gateway locations 2019-07-26 14:56:07 +01:00
ced38c6734 Refactor client-side AI into multiple web workers 2019-07-26 13:57:24 +01:00
673a8e3441 Refactor WebWorker interfacing code into own class 2019-07-26 12:33:47 +01:00
52d4f4fb38 Bugfix the new web worker.
Web workers + Tensorflow + Rollup = pain. I think I might blog about 
it....
2019-07-25 18:56:59 +01:00
4708fdbd6e Refactor the AI into a web worker, but it's untested. 2019-07-25 16:44:26 +01:00
edb6362688 Optimise client-watch by using rollup --watch 2019-07-25 14:33:02 +01:00
7a96f87b2d Bugfix: Correct latitude & longitude to make them the right way around 2019-07-25 14:02:16 +01:00
0ff5ca462e Bugfix: Correct GeoJSON 2019-07-25 13:33:11 +01:00
ff412dcd5d Update CLI help 2019-07-25 13:17:23 +01:00
dde6dc15be Create shel script proxy for server script access 2019-07-24 18:09:06 +01:00
c6e6150d3e Bugfix: Fix a bunch of crashes in the client-side map, but it's still not working :-/ 2019-07-24 18:08:53 +01:00
bd42fa29a6 Bugfix the new Leaflet AI layer, but there are still issues to work out. 2019-07-23 15:58:11 +01:00
2a065e144a Switch from path polyfill to rollup-plugin-node-builtins
Rollu  doesn't appear to like the path polyfill on npm, since it uses 
Node.js various environment features that Rollup doesn't provide
2019-07-23 15:55:29 +01:00
698e02ff52 build/client-watch: Watch for changes to the rollup config file 2019-07-23 15:53:56 +01:00
61edaf6fa3 Write AI layer, but it's untested. 2019-07-23 15:45:29 +01:00
f0694de02c Bugfix: Create 1 model per-gateway 2019-07-23 15:14:50 +01:00
225eb8753a Start setting up an AI display layer, but it's not finished yet 2019-07-23 13:49:45 +01:00
d158868c3f AITrainer: Save gateway locations to the index file 2019-07-23 13:44:00 +01:00
ebbc96ec8c HACK: Dynamically import the AITrainer when it's needed to avoid crashes when the AVX instruction set isn't available 2019-07-22 16:04:49 +01:00
a1516a67bc build: Add development web server build tasks 2019-07-22 15:47:13 +01:00
80a8833c03 [client] Get a basic map showing 2019-07-22 15:46:07 +01:00
c2810d4871 Improve format of index 2019-07-22 12:42:04 +01:00
d9cf650019 Write index JSON file to AI output directory 2019-07-22 12:40:19 +01:00
92574bc98c Serialise trained AIs and save them to disk 2019-07-22 11:53:30 +01:00
dd9d39ba52 Create initial scaffolding for client-side map interface. 2019-07-19 15:36:21 +01:00
7469d4c1bf ttn listener:Delete debug lines 2019-07-19 13:10:47 +01:00
5f5a4382a3 Move npm dependencies to top-level of repo 2019-07-19 12:12:34 +01:00
5c7cc1e906 Fix bugs in AI trainer. It works, but precisely it's doing si up for debate.... 2019-07-18 17:22:37 +01:00
192e31a925 Write the the data input, but it's untested.
There's also some confusion over the batch size. If it doesn't work, we 
probably need to  revise our understanding of the batch size in 
different contexts.
2019-07-18 16:34:25 +01:00
6dbb6c3b87 Hook up a dataset importer for training the AIs, but it's untested.
Also, we don't have any code that actually does the training itself 
either yet.
2019-07-17 15:15:31 +01:00
f7e2d77daa Start writing the AI training code, but it's not finished yet 2019-07-17 14:16:24 +01:00
1252d60af0 Default to 0600 when creating the custom settings file
The custom settings file will likely contain encryption keys and other 
sensitive data, so it's probably a good idea to tighten up the default 
permissions on it.
2019-07-16 18:08:39 +01:00
952312fbd3 Add none mode to logging.date_display_mode 2019-07-16 18:03:35 +01:00
2a9de80848 Add logging.colour settings option 2019-07-16 18:01:17 +01:00
680b5cb16e rsyslog: Fix syntax 2019-07-16 17:53:06 +01:00
883ce2b2cb rsyslog: Use stop instead of ~ 2019-07-16 17:49:11 +01:00
e65757308d ttn-server -> tth-listener 2019-07-16 17:47:59 +01:00
423d0a0dd8 Write rsyslog config file 2019-07-16 17:42:07 +01:00
abb13161da Write service file for TTN listener 2019-07-16 17:39:22 +01:00
d84d838775 Another typo 2019-07-16 16:32:24 +01:00
c703e1c2c4 typo 2019-07-16 16:14:55 +01:00