303 commits

Author	SHA1	Message	Date
Starbeamrainbowlabs	b6676e7361	switch from sparse to normal crossentropy	2022-11-10 20:50:56 +00:00
Starbeamrainbowlabs	d8be26d476	Merge branch 'main' of git.starbeamrainbowlabs.com:sbrl/PhD-Rainfall-Radar	2022-11-10 20:49:01 +00:00
Starbeamrainbowlabs	b03388de60	dataset_segmenter: DEBUG: fix water shape	2022-11-10 20:48:21 +00:00
Starbeamrainbowlabs	daf691bf43	typo	2022-11-10 19:55:00 +00:00
Starbeamrainbowlabs	0aa2ce19f5	read_metadata: support file inputs as well as dirs	2022-11-10 19:53:30 +00:00
Starbeamrainbowlabs	aa7d9b8cf6	fixup	2022-11-10 19:46:09 +00:00
Starbeamrainbowlabs	0894bd09e8	train_predict: add error message for parrams.json not found	2022-11-10 19:45:41 +00:00
Starbeamrainbowlabs	0353072d15	allow pretrain to run on gpu ... we've slashed the size of the 2nd encoder, so ti should fit naow?	2022-11-04 17:02:07 +00:00
Starbeamrainbowlabs	44ad51f483	CallbackNBatchCsv: bugfix .sort() → sorted()	2022-11-04 16:40:21 +00:00
Starbeamrainbowlabs	4dddcfcb42	pretrain_predict: missing \n	2022-11-04 16:01:28 +00:00
Starbeamrainbowlabs	1375201c5f	CallbackNBatchCsv: open_handle mode	2022-11-03 18:29:00 +00:00
Starbeamrainbowlabs	3206d6b7e7	slurm: rename segmenter job name	2022-11-03 17:12:27 +00:00
Starbeamrainbowlabs	f2ae74ce7b	how could I be so stupid..... round 2	2022-11-02 17:38:26 +00:00
Starbeamrainbowlabs	5f8d6dc6ea	Add metrics every 64 batches ... this is important, because with large batches it can be difficult to tell what's happening inside each epoch.	2022-10-31 19:26:10 +00:00
Starbeamrainbowlabs	cf872ef739	how could I be so *stupid*......	2022-10-31 18:40:58 +00:00
Starbeamrainbowlabs	da32d75778	make_callbacks: display steps, not samples	2022-10-31 18:36:28 +00:00
Starbeamrainbowlabs	dfef7db421	moar debugging	2022-10-31 18:26:34 +00:00
Starbeamrainbowlabs	172cf9d8ce	tweak	2022-10-31 18:19:43 +00:00
Starbeamrainbowlabs	dbe35ee943	loss: comment l2 norm	2022-10-31 18:09:03 +00:00
Starbeamrainbowlabs	5e60319024	fixup	2022-10-31 17:56:49 +00:00
Starbeamrainbowlabs	b986b069e2	debug party time	2022-10-31 17:50:29 +00:00
Starbeamrainbowlabs	458faa96d2	loss: fixup	2022-10-31 17:18:21 +00:00
Starbeamrainbowlabs	55dc05e8ce	contrastive: comment weights that aren't needed	2022-10-31 16:26:48 +00:00
Starbeamrainbowlabs	33391eaf16	train_predict/jsonl: don't argmax ... I'm interested inthe raw values	2022-10-26 17:21:19 +01:00
Starbeamrainbowlabs	74f2cdb900	train_predict: .list() → .tolist()	2022-10-26 17:12:36 +01:00
Starbeamrainbowlabs	4f9d543695	train_predict: don't pass model_code ... it's redundant	2022-10-26 17:11:36 +01:00
Starbeamrainbowlabs	1b489518d0	segmenter: add LayerStack2Image to custom_objects	2022-10-26 17:05:50 +01:00
Starbeamrainbowlabs	48ae8a5c20	LossContrastive: normalise features as per the paper	2022-10-26 16:52:56 +01:00
Starbeamrainbowlabs	843cc8dc7b	contrastive: rewrite the loss function. ... The CLIP paper *does* kinda make sense I think	2022-10-26 16:45:45 +01:00
Starbeamrainbowlabs	fad1399c2d	convnext: whitespace	2022-10-26 16:45:20 +01:00
Starbeamrainbowlabs	1d872cb962	contrastive: fix initial temperature value ... It should be 1/0.07, but we had it set to 0.07......	2022-10-26 16:45:01 +01:00
Starbeamrainbowlabs	f994d449f1	Layer2Image: fix	2022-10-25 21:32:17 +01:00
Starbeamrainbowlabs	6a29105f56	model_segmentation: stack not reshape	2022-10-25 21:25:15 +01:00
Starbeamrainbowlabs	98417a3e06	prepare for NCE loss ... .....but Tensorflow's implementation looks to be for supervised models :-(	2022-10-25 21:15:05 +01:00
Starbeamrainbowlabs	bb0679a509	model_segmentation: don't softmax twice	2022-10-25 21:11:48 +01:00
Starbeamrainbowlabs	f2e2ca1484	model_contrastive: make water encoder significantly shallower	2022-10-24 20:52:31 +01:00
Starbeamrainbowlabs	a6b07a49cb	count water/nowater pixels in Jupyter Notebook	2022-10-24 18:05:34 +01:00
Starbeamrainbowlabs	a8b101bdae	dataset_predict: add shape_water_desired	2022-10-24 18:05:13 +01:00
Starbeamrainbowlabs	587c1dfafa	train_predict: revamp jsonl handling	2022-10-21 16:53:08 +01:00
Starbeamrainbowlabs	8195318a42	SparseCategoricalAccuracy: losses → metrics	2022-10-21 16:51:20 +01:00
Starbeamrainbowlabs	612735aaae	rename shuffle arg	2022-10-21 16:35:45 +01:00
Starbeamrainbowlabs	c98d8d05dd	segmentation: use the right accuracy	2022-10-21 16:17:05 +01:00
Starbeamrainbowlabs	bb0258f5cd	flip squeeze operator ordering	2022-10-21 15:38:57 +01:00
Starbeamrainbowlabs	af26964c6a	batched_iterator: reset i_item after every time	2022-10-21 15:35:43 +01:00
Starbeamrainbowlabs	c5b1501dba	train-predict fixup	2022-10-21 15:27:39 +01:00
Starbeamrainbowlabs	42aea7a0cc	plt.close() fixup	2022-10-21 15:23:54 +01:00
Starbeamrainbowlabs	12dad3bc87	vis/segmentation: fix titles	2022-10-21 15:22:35 +01:00
Starbeamrainbowlabs	0cb2de5d06	train-preedict: close matplotlib after we've finished ... they act like file handles	2022-10-21 15:19:31 +01:00
Starbeamrainbowlabs	81e53efd9c	PNG: create output dir if doesn't exist	2022-10-21 15:17:39 +01:00
Starbeamrainbowlabs	3f7db6fa78	fix embedding confusion	2022-10-21 15:15:59 +01:00
Starbeamrainbowlabs	847cd97ec4	fixup	2022-10-21 14:26:58 +01:00
Starbeamrainbowlabs	0e814b7e98	Contraster → Segmenter	2022-10-21 14:25:43 +01:00
Starbeamrainbowlabs	1b658a1b7c	train-predict: can't destructure array when iterating generator ... ....it seems to lead to undefined behaviour or something	2022-10-20 19:34:04 +01:00
Starbeamrainbowlabs	aed2348a95	train_predict: fixup	2022-10-20 15:42:33 +01:00
Starbeamrainbowlabs	cc6679c609	batch data; use generator	2022-10-20 15:22:29 +01:00
Starbeamrainbowlabs	d306853c42	use right daataset	2022-10-20 15:16:24 +01:00
Starbeamrainbowlabs	59cfa4a89a	basename paths	2022-10-20 15:11:14 +01:00
Starbeamrainbowlabs	4d8ae21a45	update cli help text	2022-10-19 17:31:42 +01:00
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	7933564c66	typo	2022-10-12 17:33:54 +01:00
Starbeamrainbowlabs	dbe4fb0eab	train: add slurm job file	2022-10-12 17:27:10 +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	deede32241	slurm-pretrain: limit memory usage	2022-10-10 17:45:29 +01:00
Starbeamrainbowlabs	13a8f3f511	pretrain-predict: only queue pretrain-plot if I we output jsonl	2022-10-10 17:11:10 +01:00
Starbeamrainbowlabs	ffcb2e3735	pretrain-predict: queue for the actual input	2022-10-10 16:53:28 +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	fe813cb46d	slurm predict: fix plotting subcall	2022-10-03 16:03:26 +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