237 commits

Author	SHA1	Message	Date
Starbeamrainbowlabs	2f0ce0aa13	again	2023-01-13 18:27:03 +00:00
Starbeamrainbowlabs	e04d6ab1b6	fixup again	2023-01-13 18:23:32 +00:00
Starbeamrainbowlabs	37d1598b0b	loss cel+dice: fixup	2023-01-13 18:21:11 +00:00
Starbeamrainbowlabs	0f0b691b5d	loss cel + dice: fixup	2023-01-13 18:09:31 +00:00
Starbeamrainbowlabs	be77f035c8	dlr: add cross-entropy + dice loss fn option	2023-01-13 17:58:00 +00:00
Starbeamrainbowlabs	b2a5acaf4e	dlr dsm: clash	2023-01-13 17:26:38 +00:00
Starbeamrainbowlabs	3c4d1c5140	dlr: Add support for stripping isolated water pixels ... That is, water pixels that have no other water pixels immediately adjacent thereto (diagonals count).	2023-01-13 16:57:26 +00:00
Starbeamrainbowlabs	ce1467461d	fixup	2023-01-13 16:47:52 +00:00
Starbeamrainbowlabs	0b676fa391	move shuffle to subdir	2023-01-13 16:47:35 +00:00
Starbeamrainbowlabs	1958c4e6c2	encoderonly model: getting there	2023-01-09 19:33:41 +00:00
Starbeamrainbowlabs	52cf66ca32	start working on a quick encoder test, but it's far from finished	2023-01-06 19:55:52 +00:00
Starbeamrainbowlabs	4563fe6b27	dpl: fix moar crashes	2023-01-05 19:03:44 +00:00
Starbeamrainbowlabs	fefeb5d531	fix water depth fiddling	2023-01-05 19:01:20 +00:00
Starbeamrainbowlabs	46d1f5e4e0	dataset_mono: fix dataset parsing	2023-01-05 19:00:52 +00:00
Starbeamrainbowlabs	aca7b83a78	dataset_mono: fix sizing ... it didn't account for rainfall_scale_up	2023-01-05 18:38:47 +00:00
Starbeamrainbowlabs	19bb2fcac0	debug	2023-01-05 18:32:22 +00:00
Starbeamrainbowlabs	ef5071b569	DeepLabV3+: start working on version for rainfall radar, but it's not finished yet	2022-12-15 19:33:14 +00:00
Starbeamrainbowlabs	eb47f8f544	dataset_mono: adjust to suit DeepLabV3+ too	2022-12-13 18:37:38 +00:00
Starbeamrainbowlabs	4e4d42a281	LossDice: add comment	2022-12-12 18:34:20 +00:00
Starbeamrainbowlabs	449bc425a7	LossDice: explicitly cast inputs to float32	2022-12-12 17:20:32 +00:00
Starbeamrainbowlabs	dbf8f5617c	drop activation function in last layers	2022-12-12 17:20:04 +00:00
Starbeamrainbowlabs	bcd2f1251e	LossDice: Do 1 - thing instead of -thing	2022-12-09 19:41:32 +00:00
Starbeamrainbowlabs	d0dbc50bb7	debug	2022-12-09 19:33:28 +00:00
Starbeamrainbowlabs	2142bb039c	again	2022-12-09 19:30:01 +00:00
Starbeamrainbowlabs	7000b0f193	fixup	2022-12-09 19:23:35 +00:00
Starbeamrainbowlabs	85012d0616	fixup	2022-12-09 19:18:03 +00:00
Starbeamrainbowlabs	719d8e9819	strip channels layer at end	2022-12-09 19:11:00 +00:00
Starbeamrainbowlabs	0129c35a35	LossDice: remove weird K.* functions	2022-12-09 19:06:26 +00:00
Starbeamrainbowlabs	659fc97fd4	fix crash	2022-12-09 18:39:27 +00:00
Starbeamrainbowlabs	e22c0981e6	actually use dice loss	2022-12-09 18:35:17 +00:00
Starbeamrainbowlabs	649c262960	mono: switch loss from crossentropy to dice	2022-12-09 18:13:37 +00:00
Starbeamrainbowlabs	2a1772a211	confvnext_intrevse: add shallow	2022-12-08 19:10:12 +00:00
Starbeamrainbowlabs	3dde9b69da	fixup	2022-12-08 18:56:32 +00:00
Starbeamrainbowlabs	6fce39f696	WHY?!?!?!	2022-12-08 18:55:53 +00:00
Starbeamrainbowlabs	26766366fc	I hate the python code intelligence ... it's bad	2022-12-08 18:55:15 +00:00
Starbeamrainbowlabs	ff56f591c7	I hate python	2022-12-08 18:53:37 +00:00
Starbeamrainbowlabs	d37e7224f5	train-mono: tidy up arg passing	2022-12-08 18:47:03 +00:00
Starbeamrainbowlabs	b53db648bf	fixup	2022-12-08 18:31:42 +00:00
Starbeamrainbowlabs	18c0210704	typo	2022-12-08 17:00:25 +00:00
Starbeamrainbowlabs	a3c9416cf0	LossCrossentropy: don't sum	2022-12-08 16:57:11 +00:00
Starbeamrainbowlabs	08046340f4	dataset_mono: normalise heightmap	2022-12-08 16:10:34 +00:00
Starbeamrainbowlabs	d997157f55	dataset_mono: log when using heightmap	2022-12-06 19:30:11 +00:00
Starbeamrainbowlabs	d0f2e3d730	readfile: do transparent gzip by default ... ....but there's a glad to turn it off if needed	2022-12-06 19:27:39 +00:00
Starbeamrainbowlabs	eac6472c97	Implement support for (optionally) taking a heightmap in	2022-12-06 18:55:58 +00:00
Starbeamrainbowlabs	f92b2b3472	according to the equation it looks like it's 2	2022-12-02 17:22:46 +00:00
Starbeamrainbowlabs	cad82cd1bc	CBAM: unsure if it's 1 ro 3 dense ayers in the shared mlp	2022-12-02 17:21:13 +00:00
Starbeamrainbowlabs	62f6a993bb	implement CBAM, but it's UNTESTED ... Convolutional Block Attention Module.	2022-12-02 17:17:45 +00:00
Starbeamrainbowlabs	53dfa32685	model_mono: log learning rate	2022-12-01 15:10:51 +00:00
Starbeamrainbowlabs	c384d55dff	add arg to adjust learning rate	2022-11-29 20:55:00 +00:00
Starbeamrainbowlabs	8e23e9d341	model_segmenter: we're no longer using sparse	2022-11-29 19:28:27 +00:00