292 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
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	4ceec73e5b	Merge branch 'main' of git.starbeamrainbowlabs.com:sbrl/PhD-Rainfall-Radar	2022-10-18 19:07:23 +01:00