363 commits

Author	SHA1	Message	Date
Starbeamrainbowlabs	200076596b	finish train_predict	2022-10-19 17:26:40 +01:00
Starbeamrainbowlabs	488f78fca5	pretrain_predict: default to parallel_reads=0	2022-10-19 16:59:45 +01:00
Starbeamrainbowlabs	63e909d9fc	datasets: add shuffle=True/False to get_filepaths. ... This is important because otherwise it SCAMBLES the filenames, which is a disaster for making predictions in the right order....!	2022-10-19 16:52:07 +01:00
Starbeamrainbowlabs	fe43ddfbf9	start implementing driver for train_predict, but not finished yet	2022-10-18 19:37:55 +01:00
Starbeamrainbowlabs	b3ea189d37	segmentation: softmax the output	2022-10-13 21:02:57 +01:00
Starbeamrainbowlabs	f121bfb981	fixup summaryfile	2022-10-13 17:54:42 +01:00
Starbeamrainbowlabs	5c35c0cee4	model_segmentation: document; remove unused args	2022-10-13 17:50:16 +01:00
Starbeamrainbowlabs	f12e6ab905	No need for a CLI arg for feature_dim_in - metadata should contain this	2022-10-13 17:37:16 +01:00
Starbeamrainbowlabs	e201372252	write quick Jupyter notebook to test data ... ....I'm paranoid	2022-10-13 17:27:17 +01:00
Starbeamrainbowlabs	ae53130e66	layout	2022-10-13 14:54:20 +01:00
Starbeamrainbowlabs	6423bf6702	LayerConvNeXtGamma: avoid adding an EagerTensor to config ... Very weird how this is a problem when it wasn't before..	2022-10-12 17:12:07 +01:00
Starbeamrainbowlabs	32f5200d3b	pass model_arch properly	2022-10-12 16:50:06 +01:00
Starbeamrainbowlabs	5933fb1061	fixup	2022-10-11 19:23:41 +01:00
Starbeamrainbowlabs	c45b90764e	segmentation: adds xxtiny, but unsure if it's small enough	2022-10-11 19:22:37 +01:00
Starbeamrainbowlabs	f4a2c742d9	typo	2022-10-11 19:19:23 +01:00
Starbeamrainbowlabs	11f91a7cf4	train: add --arch; default to convnext_i_xtiny	2022-10-11 19:18:01 +01:00
Starbeamrainbowlabs	5666c5a0d9	typo	2022-10-10 18:12:51 +01:00
Starbeamrainbowlabs	131c0a0a5b	pretrain-predict: create dir if not exists	2022-10-10 18:00:55 +01:00
Starbeamrainbowlabs	f883986eaa	Bugfix: modeset to enable TFRecordWriter instead of bare handle	2022-10-06 20:07:59 +01:00
Starbeamrainbowlabs	e9a8e2eb57	fixup	2022-10-06 19:23:31 +01:00
Starbeamrainbowlabs	9f3ae96894	finish wiring for --water-size	2022-10-06 19:21:50 +01:00
Starbeamrainbowlabs	5dac70aa08	typo	2022-10-06 19:17:03 +01:00
Starbeamrainbowlabs	2960d3b645	exception → warning	2022-10-06 18:26:40 +01:00
Starbeamrainbowlabs	0ee6703c1e	Add todo and comment	2022-10-03 19:06:56 +01:00
Starbeamrainbowlabs	2b182214ea	typo	2022-10-03 17:53:10 +01:00
Starbeamrainbowlabs	92c380bff5	fiddle with Conv2DTranspose ... you need to set the `stride` argument to actually get it to upscale..... :P	2022-10-03 17:51:41 +01:00
Starbeamrainbowlabs	d544553800	fixup	2022-10-03 17:33:06 +01:00
Starbeamrainbowlabs	058e3b6248	model_segmentation: cast float → int	2022-10-03 17:31:36 +01:00
Starbeamrainbowlabs	04e5ae0c45	model_segmentation: redo reshape ... much cheese was applied :P	2022-10-03 17:27:52 +01:00
Starbeamrainbowlabs	deffe69202	typo	2022-10-03 16:59:36 +01:00
Starbeamrainbowlabs	fc6d2dabc9	Upscale first, THEN convnext...	2022-10-03 16:38:43 +01:00
Starbeamrainbowlabs	6a0790ff50	convnext_inverse: add returns; change ordering	2022-10-03 16:32:09 +01:00
Starbeamrainbowlabs	e51087d0a9	add reshape layer	2022-09-28 18:22:48 +01:00
Starbeamrainbowlabs	a336cdee90	and continues	2022-09-28 18:18:10 +01:00
Starbeamrainbowlabs	de47a883d9	missing units	2022-09-28 18:17:22 +01:00
Starbeamrainbowlabs	b5e08f92fe	the long night continues	2022-09-28 18:14:09 +01:00
Starbeamrainbowlabs	dc159ecfdb	and again	2022-09-28 18:11:46 +01:00
Starbeamrainbowlabs	4cf0485e32	fixup... again	2022-09-28 18:10:11 +01:00
Starbeamrainbowlabs	030d8710b6	fixup	2022-09-28 18:08:31 +01:00
Starbeamrainbowlabs	4ee7f2a0d6	add water thresholding	2022-09-28 18:07:26 +01:00
Starbeamrainbowlabs	404dc30f08	and again	2022-09-28 17:39:09 +01:00
Starbeamrainbowlabs	4cd8fc6ded	segmentation: param name fix	2022-09-28 17:37:42 +01:00
Starbeamrainbowlabs	41ba980d69	segmentationP implement dataset parser	2022-09-28 17:19:21 +01:00
Starbeamrainbowlabs	d618e6f8d7	pretrain-predict: params.json → metadata.jsonl	2022-09-28 16:35:22 +01:00
Starbeamrainbowlabs	e9e6139c7a	typo	2022-09-28 16:28:18 +01:00
Starbeamrainbowlabs	3dee3d8908	update cli help	2022-09-28 16:23:47 +01:00
Starbeamrainbowlabs	d765b3b14e	fix crash	2022-09-27 18:43:43 +01:00
Starbeamrainbowlabs	f4d1d1d77e	just wh	2022-09-27 18:25:45 +01:00
Starbeamrainbowlabs	4c24d69ae6	$d → +d	2022-09-27 18:17:07 +01:00
Starbeamrainbowlabs	cdb19b4d9f	fixup	2022-09-27 18:13:21 +01:00
Starbeamrainbowlabs	c4d3c16873	add some logging	2022-09-27 18:10:58 +01:00
Starbeamrainbowlabs	3772c3227e	fixup	2022-09-27 17:57:21 +01:00
Starbeamrainbowlabs	dbfa45a016	write params.json properly	2022-09-27 17:49:54 +01:00
Starbeamrainbowlabs	a5455dc22a	fix import	2022-09-27 17:41:24 +01:00
Starbeamrainbowlabs	d6ff3fb2ce	pretrain_predict fix write mode	2022-09-27 17:38:12 +01:00
Starbeamrainbowlabs	f95fd8f9e4	pretrain-predict: add .tfrecord output function	2022-09-27 16:59:31 +01:00
Starbeamrainbowlabs	30b8dd063e	fixup	2022-09-27 15:54:37 +01:00
Starbeamrainbowlabs	3cf99587e4	Contraster: add gamma layer to load_model	2022-09-27 15:53:52 +01:00
Starbeamrainbowlabs	9e9852d066	UMAP: 100k random ... no labels.	2022-09-27 15:52:45 +01:00
Starbeamrainbowlabs	d59de41ebb	embeddings: change title rendering; make even moar widererer ... We need to see that parallel coordinates plot in detail	2022-09-23 18:56:39 +01:00
Starbeamrainbowlabs	5252a81238	vis: don't call add_subplot	2022-09-20 19:06:21 +01:00
Starbeamrainbowlabs	a552cc4dad	ai vis: make parallel coordinates wider	2022-09-16 18:51:49 +01:00
Starbeamrainbowlabs	a70794e661	umap: no min_dist	2022-09-16 17:09:09 +01:00
Starbeamrainbowlabs	5778fc51f7	embeddings: fix title; remove colourmap	2022-09-16 17:08:04 +01:00
Starbeamrainbowlabs	4fd852d782	fixup	2022-09-16 16:44:35 +01:00
Starbeamrainbowlabs	fcab227f6a	cheese: set label for everything to 1	2022-09-16 16:42:05 +01:00
Starbeamrainbowlabs	b31645bd5d	pretrain-plot: fix crash; remove water code ... the model doesn't save the water encoder at this time	2022-09-16 16:24:07 +01:00
Starbeamrainbowlabs	a5f03390ef	pretrain-plot: handle open w -> r	2022-09-16 16:14:30 +01:00
Starbeamrainbowlabs	1103ae5561	ai: tweak progress bar	2022-09-16 16:07:16 +01:00
Starbeamrainbowlabs	1e35802d2b	ai: fix embed i/o	2022-09-16 16:02:27 +01:00
Starbeamrainbowlabs	ed94da7492	fixup	2022-09-16 15:51:26 +01:00
Starbeamrainbowlabs	366db658a8	ds predict: fix filenames in	2022-09-16 15:45:22 +01:00
Starbeamrainbowlabs	e333dcba9c	tweak projection head	2022-09-16 15:36:01 +01:00
Starbeamrainbowlabs	6defd24000	bugfix: too many values to unpack	2022-09-15 19:56:17 +01:00
Starbeamrainbowlabs	e3c8277255	ai: tweak the segmentation model structure	2022-09-15 19:54:50 +01:00
Starbeamrainbowlabs	1bc8a5bf13	ai: fix crash	2022-09-15 19:37:06 +01:00
Starbeamrainbowlabs	bd64986332	ai: implement batched_iterator to replace .batch() ... ...apparently .batch() means you get a BatchedDataset or whatever when you iterate it like a tf.function instead of the actual tensor :-/	2022-09-15 19:16:38 +01:00
Starbeamrainbowlabs	ccd256c00a	embed rainfall radar, not both	2022-09-15 17:37:04 +01:00
Starbeamrainbowlabs	2c74676902	predict → predict_on_batch	2022-09-15 17:31:50 +01:00
Starbeamrainbowlabs	f036e79098	fixup	2022-09-15 17:09:26 +01:00
Starbeamrainbowlabs	d5f1a26ba3	disable prefetching when predicting a thing	2022-09-15 17:09:09 +01:00
Starbeamrainbowlabs	8770638022	ai: call .predict(), not the model itself	2022-09-14 17:41:01 +01:00
Starbeamrainbowlabs	a96cefde62	ai: predict oops	2022-09-14 17:37:48 +01:00
Starbeamrainbowlabs	fa3165a5b2	dataset: simplify dataset_predict	2022-09-14 17:33:17 +01:00
Starbeamrainbowlabs	279e27c898	fixup	2022-09-14 17:16:49 +01:00
Starbeamrainbowlabs	fad3313ede	fixup	2022-09-14 17:14:04 +01:00
Starbeamrainbowlabs	1e682661db	ai: kwargs in from_checkpoint	2022-09-14 17:11:06 +01:00
Starbeamrainbowlabs	6bda24d4da	ai: how did I miss that?! ... bugfix ah/c	2022-09-14 16:53:43 +01:00
Starbeamrainbowlabs	decdd434d8	ai from_checkpoint: bugfix	2022-09-14 16:49:01 +01:00
Starbeamrainbowlabs	c9e00ea485	pretrain_predict: fix import	2022-09-14 16:02:36 +01:00
Starbeamrainbowlabs	f568d8d19f	io.open → handle_open ... this was we get transparent .gz support	2022-09-14 16:01:22 +01:00
Starbeamrainbowlabs	9b25186541	fix --only-gpu	2022-09-14 15:55:21 +01:00
Starbeamrainbowlabs	1876a8883c	ai pretrain-predict: fix - → _ in cli parsing	2022-09-14 15:12:07 +01:00
Starbeamrainbowlabs	f97b771922	make --help display help	2022-09-14 15:03:07 +01:00
Starbeamrainbowlabs	3c1aef5913	update help	2022-09-13 19:36:56 +01:00
Starbeamrainbowlabs	206257f9f5	ai pretrain_predict: no need to plot here anymore	2022-09-13 19:35:44 +01:00
Starbeamrainbowlabs	7685ec3e8b	implement ability to embed & plot pretrained embeddings	2022-09-13 19:18:59 +01:00
Starbeamrainbowlabs	7130c4fdf8	start implementing core image segmentation model	2022-09-07 17:45:38 +01:00
Starbeamrainbowlabs	22620a1854	ai: implement saving only the rainfall encoder	2022-09-06 19:48:46 +01:00
Starbeamrainbowlabs	4c4358c3e5	whitespace	2022-09-06 16:24:11 +01:00
Starbeamrainbowlabs	4202821d98	typo	2022-09-06 15:37:36 +01:00
Starbeamrainbowlabs	3e13ad12c8	ai Bugfix LayerContrastiveEncoder: channels → input_channels ... for consistency	2022-09-05 23:53:16 +01:00
Starbeamrainbowlabs	ead8009425	pretrain: add CLI arg for size of watch prediction width/height	2022-09-05 15:36:40 +01:00
Starbeamrainbowlabs	9d39215dd5	dataset: drop incomplete batches	2022-09-05 15:36:10 +01:00
Starbeamrainbowlabs	1d1533d160	ai: how did things get this confusing	2022-09-02 18:51:46 +01:00
Starbeamrainbowlabs	1c5defdcd6	ai: cats	2022-09-02 18:45:23 +01:00
Starbeamrainbowlabs	6135bcd0cd	fixup	2022-09-02 18:41:31 +01:00
Starbeamrainbowlabs	c33c0a0899	ai: these shapes are so annoying	2022-09-02 18:39:24 +01:00
Starbeamrainbowlabs	88acd54a97	ai: off-by-one	2022-09-02 18:13:48 +01:00
Starbeamrainbowlabs	23bcd294c4	AI: 0.75 → 0.5?	2022-09-02 18:12:51 +01:00
Starbeamrainbowlabs	b0e1aeac35	ai: knew it	2022-09-02 18:10:29 +01:00
Starbeamrainbowlabs	ef0f15960d	send correct water shape to	2022-09-02 18:09:36 +01:00
Starbeamrainbowlabs	ad156a9a00	ai dataset: centre crop the water data to 75% original size ... this should both help the model and reduce memory usage	2022-09-02 18:05:32 +01:00
Starbeamrainbowlabs	efe41b96ec	fixup	2022-09-02 17:58:02 +01:00
Starbeamrainbowlabs	f8ee0afca1	ai: fix arch_name plumbing	2022-09-02 17:57:07 +01:00
Starbeamrainbowlabs	3d44831080	Add NO_PREFETCH env var	2022-09-02 17:55:04 +01:00
Starbeamrainbowlabs	3e0ca6a315	ai: fix summary file writing; make water encoder smaller	2022-09-02 17:51:45 +01:00
Starbeamrainbowlabs	389216b391	reordering	2022-09-02 17:31:19 +01:00
Starbeamrainbowlabs	b9d01ddadc	summary logger → summarywriter	2022-09-02 17:28:00 +01:00
Starbeamrainbowlabs	9f7f4af784	dataset: properly resize	2022-09-02 17:09:38 +01:00
Starbeamrainbowlabs	c78b6562ef	debug adjustment	2022-09-02 17:00:21 +01:00
Starbeamrainbowlabs	c89677abd7	dataset: explicit reshape	2022-09-02 16:57:59 +01:00
Starbeamrainbowlabs	c066ea331b	dataset: namespace → dict ... Python is so annoying	2022-09-02 16:07:44 +01:00
Starbeamrainbowlabs	dbff15d4a9	add bug comment	2022-09-01 19:05:50 +01:00
Starbeamrainbowlabs	3e4128c0a8	resize rainfall to be 1/2 size of current	2022-09-01 18:47:07 +01:00
Starbeamrainbowlabs	8a86728b54	ai: how did I miss that	2022-09-01 18:07:53 +01:00
Starbeamrainbowlabs	b2f1ba29bb	debug a	2022-09-01 18:05:33 +01:00
Starbeamrainbowlabs	e2f621e212	even moar debug logging	2022-09-01 17:49:51 +01:00
Starbeamrainbowlabs	2663123407	moar logging	2022-09-01 17:40:23 +01:00
Starbeamrainbowlabs	c2fcb3b954	ai: channels_first → channels_last	2022-09-01 17:06:18 +01:00
Starbeamrainbowlabs	f1d7973f22	ai: add dummy label	2022-09-01 17:01:00 +01:00
Starbeamrainbowlabs	17d42fe899	ai: json.dumps	2022-09-01 16:21:52 +01:00
Starbeamrainbowlabs	940f7aa1b5	ai: set self.model	2022-09-01 16:20:23 +01:00
Starbeamrainbowlabs	f1be5fe2bd	ai: add missing arguments to LossContrastive	2022-09-01 16:14:00 +01:00
Starbeamrainbowlabs	ddb375e906	ai: another typo	2022-09-01 16:12:05 +01:00
Starbeamrainbowlabs	cb3e1d3a23	ai: fixup	2022-09-01 16:10:50 +01:00
Starbeamrainbowlabs	e4c95bc7e3	typo	2022-09-01 16:09:24 +01:00
Starbeamrainbowlabs	cfbbe8e8cf	ai: global? really?	2022-09-01 16:06:24 +01:00
Starbeamrainbowlabs	4952ead094	ai: try the nonlocal keyword? I'm unsure what's going on here ... ....clearly I need to read up on scoping in python.	2022-09-01 16:02:37 +01:00
Starbeamrainbowlabs	8bdded23eb	ai: fix 'nother crash' name ConvNeXt submodels	2022-08-31 18:57:27 +01:00
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	dbf929325a	typo; add pretrain slurm job file	2022-08-31 16:32:17 +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	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