Starbeamrainbowlabs
b2a320134e
ai: typo
2022-08-31 18:54:03 +01:00
Starbeamrainbowlabs
e4edc68df5
ai: add missing gamma layer
2022-08-31 18:52:35 +01:00
Starbeamrainbowlabs
51cf08a386
ResNetRSV2 → ConvNeXt
...
ironically this makes the model simpler o/
2022-08-31 18:51:01 +01:00
Starbeamrainbowlabs
3d614d105b
channels first
2022-08-31 18:06:59 +01:00
Starbeamrainbowlabs
654eefd9ca
properly handle water dimensions; add log files to .gitignore
...
TODO: add heightmap
2022-08-31 18:03:39 +01:00
Starbeamrainbowlabs
5846828f9e
debug logging
2022-08-31 17:48:09 +01:00
Starbeamrainbowlabs
12c77e128d
handle feature_dim properly
2022-08-31 17:41:51 +01:00
Starbeamrainbowlabs
c52a9f961c
and another
2022-08-31 17:37:28 +01:00
Starbeamrainbowlabs
58dbabd561
fix another crash
2022-08-31 17:33:07 +01:00
Starbeamrainbowlabs
5fc0725917
slurm: chmod +x
2022-08-31 16:33:07 +01:00
Starbeamrainbowlabs
dbf929325a
typo; add pretrain slurm job file
2022-08-31 16:32:17 +01:00
Starbeamrainbowlabs
e0162bc70b
requirements.txt: add missing dependencies
2022-08-31 16:25:47 +01:00
Starbeamrainbowlabs
f2312c1184
fix crash
2022-08-31 16:25:27 +01:00
Starbeamrainbowlabs
15a3519107
ai: the best thing about implementing a model is that you don't have to test it on the same day :P
2022-08-11 18:26:28 +01:00
Starbeamrainbowlabs
c0a9cb12d8
ai: start creating initial model implementation.
...
it's not hooked up to the CLI yet though.
Focus is still on ensuring the dataset is in the right format though
2022-08-10 19:03:25 +01:00
Starbeamrainbowlabs
b52c7f89a7
Move dataset parsing function to the right place
2022-08-10 17:24:55 +01:00
Starbeamrainbowlabs
222a6146ec
write glue for .jsonl.gz → .tfrecord.gz converter
2022-08-08 15:33:59 +01:00
Starbeamrainbowlabs
28a3f578d5
update .gitignore
2022-08-04 16:49:53 +01:00
Starbeamrainbowlabs
323d708692
dataset: add todo
...
just why, Tensorflow?!
tf.data.TextLineDataset looks almost too good to be true..... and it is, as despite supporting decompressing via gzip(!) it doesn't look like we can convince it to parse JSON :-/
2022-07-26 19:53:18 +01:00
Starbeamrainbowlabs
b53c77a2cb
index.py: call static function name run
2022-07-26 19:51:28 +01:00
Starbeamrainbowlabs
a7ed58fc03
ai: move requirements.txt to the right place
2022-07-26 19:25:11 +01:00
Starbeamrainbowlabs
e93a95f1b3
ai dataset: add if main == main
2022-07-26 19:24:40 +01:00
Starbeamrainbowlabs
de4c3dab17
typo
2022-07-26 19:14:55 +01:00
Starbeamrainbowlabs
18a7d3674b
ai: create (untested) dataset
2022-07-26 19:14:10 +01:00
Starbeamrainbowlabs
dac6919fcd
ai: start creating initial scaffolding
2022-07-25 19:01:10 +01:00
Starbeamrainbowlabs
8a9cd6c1c0
Lay out some basic scaffolding
...
I *really* hope this works. This is the 3rd major revision of this
model. I've learnt a ton of stuff between now and my last attempt, so
here's hoping that all goes well :D
The basic idea behind this attempt is *Contrastive Learning*. If we
don't get anything useful with this approach, then we can assume that
it's not really possible / feasible.
Something we need to watch out for is the variance (or rather lack
thereof) in the dataset. We have 1.5M timesteps, but not a whole lot
will be happening in most of those....
We may need to analyse the variance of the water depth data and extract
a subsample that's more balanced.
2022-05-13 19:06:15 +01:00