557 commits

Author	SHA1	Message	Date
Starbeamrainbowlabs	dddc08c663	dlr: set steps_per_execution to 16 by default	2023-05-04 18:13:08 +01:00
Starbeamrainbowlabs	e2e6a56b40	dlr: add UPSAMPLE env var ... ...AND actually add the functionality this time!	2023-05-04 17:40:16 +01:00
Starbeamrainbowlabs	31687da931	celldice: actually do log(cosh()) ... ....just wow.	2023-05-03 15:00:10 +01:00
Starbeamrainbowlabs	4a4df380e3	if name == main	2023-03-23 18:09:52 +00:00
Starbeamrainbowlabs	81cad8e6b4	newline	2023-03-23 18:01:21 +00:00
Starbeamrainbowlabs	1bd59dc038	finish script to plot generic metrics	2023-03-23 18:00:00 +00:00
Starbeamrainbowlabs	698bbe2ffb	start working on plotting script, but it isn't finished yet	2023-03-22 17:45:06 +00:00
Starbeamrainbowlabs	6b17d45aad	dlr: plot all metrics	2023-03-22 17:41:34 +00:00
Starbeamrainbowlabs	e565c36149	deeplabv3+: prepare for ConvNeXt	2023-03-14 21:51:41 +00:00
Starbeamrainbowlabs	779b546897	dlr: log new env vars	2023-03-14 20:28:22 +00:00
Starbeamrainbowlabs	623208ba6d	dlr: add env var for water thresholding	2023-03-14 20:18:39 +00:00
Starbeamrainbowlabs	c5fc62c411	dlr CHANGE: Add optional log(cosh(dice_loss)) ... Ref https://doi.org/10.1109/cibcb48159.2020.9277638	2023-03-10 20:24:13 +00:00
Starbeamrainbowlabs	f25d1b5b1a	dlr CHANGE: properly normalise the heightmap	2023-03-10 19:13:32 +00:00
Starbeamrainbowlabs	8e76ac2864	dlr: typo	2023-03-10 17:40:16 +00:00
Starbeamrainbowlabs	5e79825292	dlr: tf.Tensor → numpy array → list → json → disk	2023-03-10 17:34:49 +00:00
Starbeamrainbowlabs	b287970032	dlr: missing import	2023-03-10 17:31:03 +00:00
Starbeamrainbowlabs	e6cd0aa1b9	dlr: fix crash	2023-03-10 17:14:06 +00:00
Starbeamrainbowlabs	cf37aeb11a	dlr: truncate jsonl before we start to avoid mixing things up	2023-03-10 17:11:10 +00:00
Starbeamrainbowlabs	5fdf229d06	dlr: write raw outputs to jsonl file	2023-03-10 17:07:44 +00:00
Starbeamrainbowlabs	d24381babb	dlr: make size fo prediction graph actually sensible	2023-03-09 19:54:27 +00:00
Starbeamrainbowlabs	8d932757b5	dlr: variable name typo	2023-03-09 19:44:39 +00:00
Starbeamrainbowlabs	b6ca885fe2	dlr: told you so	2023-03-09 19:43:35 +00:00
Starbeamrainbowlabs	f9df19cfd5	dlr: next of several typos	2023-03-09 19:34:45 +00:00
Starbeamrainbowlabs	96eae636ea	dir: add missing functions to .load() custom objs ... apparently metrics are also required to be included here...	2023-03-09 19:26:57 +00:00
Starbeamrainbowlabs	ad52ae9241	dir: also plot inputs	2023-03-09 19:13:25 +00:00
Starbeamrainbowlabs	436ab78438	dlr: when predicting, also display heatmap ... ...of positive predictions	2023-03-09 18:54:28 +00:00
Starbeamrainbowlabs	5195fe6b62	jupyter test: heatmaps in matplotlib & seaborn	2023-03-09 18:52:56 +00:00
Starbeamrainbowlabs	45c76ba252	typo	2023-03-03 22:46:02 +00:00
Starbeamrainbowlabs	c909cfd3d1	fixup	2023-03-03 22:45:34 +00:00
Starbeamrainbowlabs	0734201107	dlr: tf graph changes	2023-03-03 22:44:49 +00:00
Starbeamrainbowlabs	750f46dbd2	debug	2023-03-03 22:39:30 +00:00
Starbeamrainbowlabs	5472729f5e	dlr: fixup argmax & y_true/y_pred	2023-03-03 22:37:36 +00:00
Starbeamrainbowlabs	bc734a29c6	y_true is one-hot, convert to sparse	2023-03-03 22:20:11 +00:00
Starbeamrainbowlabs	c7b577ab29	specificity: convert to plaintf	2023-03-03 22:16:48 +00:00
Starbeamrainbowlabs	26cc824ace	dlr: MeanIoU fixup	2023-03-03 22:10:49 +00:00
Starbeamrainbowlabs	e9dcbe3863	dlr: fixup	2023-03-03 22:09:05 +00:00
Starbeamrainbowlabs	5c6789bf40	meaniou: implement one-hot version ... it expects sparse, but our output is one-hot.	2023-03-03 22:04:21 +00:00
Starbeamrainbowlabs	6ffda40d48	fixup	2023-03-03 21:54:45 +00:00
Starbeamrainbowlabs	9b13e9ca5b	dlr: fixup argmax first	2023-03-03 21:51:24 +00:00
Starbeamrainbowlabs	7453c607ed	argmax for sensitivity & specificity too	2023-03-03 21:49:33 +00:00
Starbeamrainbowlabs	8470aec996	dlr: fixup	2023-03-03 21:45:51 +00:00
Starbeamrainbowlabs	3d051a8874	dlr: HACK: argmax to convert [64,128,128, 2] → [64,128,128]	2023-03-03 21:41:26 +00:00
Starbeamrainbowlabs	94a32e7144	dlr: fix metrics	2023-03-03 20:37:22 +00:00
Starbeamrainbowlabs	c7f96ab6ab	dlr: typo	2023-03-03 20:23:03 +00:00
Starbeamrainbowlabs	06f956dc07	dlr: default LOSS, EPOCHS, and PREDICT_COUNT to better values ... Ref recent experiments	2023-03-03 20:17:08 +00:00
Starbeamrainbowlabs	b435cc54dd	dlr: add sensitivity (aka recall) and specificity metrics	2023-03-03 20:00:05 +00:00
Starbeamrainbowlabs	483ecf11c8	add specificity metric	2023-03-03 19:35:20 +00:00
Starbeamrainbowlabs	d464c9f57d	dlr: add dice loss as metric ... more metrics to go tho	2023-03-03 19:34:55 +00:00
Starbeamrainbowlabs	f70083bea4	dlr eo: set custom_objects when loading model	2023-03-01 17:19:10 +00:00
Starbeamrainbowlabs	b5f23e76d1	dlr eo: allow setting DIR_OUTPUT directly	2023-03-01 16:54:15 +00:00
Starbeamrainbowlabs	4fd9feba4f	dlr eo: tidyup	2023-03-01 16:47:36 +00:00
Starbeamrainbowlabs	69b5ae8838	dlr eo: this should fix it	2023-02-23 17:24:30 +00:00
Starbeamrainbowlabs	9f1cee2927	dlr eo: cheese it by upsampling and then downsampling again	2023-02-23 16:47:00 +00:00
Starbeamrainbowlabs	96b94ec55b	upsampling test	2023-02-23 16:19:44 +00:00
Starbeamrainbowlabs	747ddfd41b	weird, XLA_FLAGS cuda data dir wasn't needed before ... libdevice not found at ./libdevice.10.bc	2023-02-10 13:28:34 +00:00
Starbeamrainbowlabs	e43274cd91	dlr eo: add VAL_STEPS_PER_EPOCH	2023-02-03 16:41:30 +00:00
Starbeamrainbowlabs	8446a842d1	typo	2023-02-03 16:01:54 +00:00
Starbeamrainbowlabs	1a8f10339a	LayerConvNeXtGamma: fix for mixed precision mode	2023-02-02 16:22:08 +00:00
Starbeamrainbowlabs	a630db2c49	dlr eo: fixup	2023-02-02 16:17:52 +00:00
Starbeamrainbowlabs	2bf1872aca	dlr eo: add JIT_COMPILE and MIXED_PRECISION	2023-02-02 16:14:09 +00:00
Starbeamrainbowlabs	71088b8c0b	typo	2023-02-02 15:48:49 +00:00
Starbeamrainbowlabs	f7666865a0	dlr eo: add STEPS_PER_EXECUTION	2023-02-02 15:47:08 +00:00
Starbeamrainbowlabs	f8202851a1	dlr eo: add LEARNING_RATE	2023-01-27 16:51:13 +00:00
Starbeamrainbowlabs	fb898ea72b	slurm eo: seriously....?	2023-01-26 17:02:33 +00:00
Starbeamrainbowlabs	be946091b1	slurm eo: DIR_OUTPUT → DIRPATH_OUTPUT	2023-01-26 16:52:14 +00:00
Starbeamrainbowlabs	4703bdbea1	SLURM: add job file for encoderonly ... It's pretty much bugfixed, but illykin doesn't have enough RAM to support it at the moment :-(	2023-01-20 20:32:35 +00:00
Starbeamrainbowlabs	818d77c733	Make dirpath_rainfallwater consistent with other experiments	2023-01-20 20:31:26 +00:00
Starbeamrainbowlabs	e72d3991b8	switch to a smaller ConvNeXt	2023-01-20 19:14:38 +00:00
Starbeamrainbowlabs	e1ad16a213	debug A	2023-01-20 18:58:45 +00:00
Starbeamrainbowlabs	65a2e16a4c	ds_eo: lower memory usage	2023-01-20 18:55:52 +00:00
Starbeamrainbowlabs	b5e68fc1a3	eo: don't downsample ConvNeXt at beginning	2023-01-20 18:49:46 +00:00
Starbeamrainbowlabs	d5fdab50ed	dlreo: missing import	2023-01-20 18:40:35 +00:00
Starbeamrainbowlabs	4514086dc6	make_encoderonly: kwargs	2023-01-20 18:39:35 +00:00
Starbeamrainbowlabs	35dbd3f8bc	ds eo: scale up rainfall data ... It's taken most fo the afternoon to spot this one 🤦	2023-01-20 18:37:08 +00:00
Starbeamrainbowlabs	5b54ceec48	ds eo: debug	2023-01-20 18:36:14 +00:00
Starbeamrainbowlabs	a3787f0647	debug	2023-01-20 18:34:56 +00:00
Starbeamrainbowlabs	9bd5e0f7a3	ds_eo: debug ... there's something fishy going on here.	2023-01-20 17:25:22 +00:00
Starbeamrainbowlabs	aa3831bc4f	ds_eo: pass water to reshape	2023-01-17 19:07:16 +00:00
Starbeamrainbowlabs	a01c49414f	ds_eo: typo	2023-01-17 19:06:29 +00:00
Starbeamrainbowlabs	b9bea26d26	ds_eo: rogue variables	2023-01-17 19:03:14 +00:00
Starbeamrainbowlabs	64c57bbc21	dlr: add no-requeue ... Ref https://support.hull.ac.uk/tas/public/ssp/content/detail/incident?unid=652db7ac6e73485c9f7658db78b2b628	2023-01-17 18:20:26 +00:00
Starbeamrainbowlabs	a28bbb9cf7	encoderonly: make executable	2023-01-17 17:55:10 +00:00
Starbeamrainbowlabs	835b376c72	slurm dlr: log exit code	2023-01-17 15:18:26 +00:00
Starbeamrainbowlabs	40a550f155	slurm dlr: fixup	2023-01-16 18:45:08 +00:00
Starbeamrainbowlabs	7bcf13f8d8	dlr: typo	2023-01-16 18:02:09 +00:00
Starbeamrainbowlabs	6ff2864d23	slurm dlr: shell out in conda; redirect stderr & stdout to disk inside the experiments folder ... Also, if the job restarts, we still save the previous run's results because we append rather than overwrite	2023-01-16 17:32:22 +00:00
Starbeamrainbowlabs	0b31c9e700	log start time, end time, and elapsed ... just in case...!	2023-01-16 17:30:20 +00:00
Starbeamrainbowlabs	1a4ac3ed66	encoderonly: add graph plotting	2023-01-13 19:08:38 +00:00
Starbeamrainbowlabs	82e01da70b	fixup.... again ... oops	2023-01-13 18:47:29 +00:00
Starbeamrainbowlabs	7b10f5c5fe	dlr: add learning_rate env var	2023-01-13 18:29:39 +00:00
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	f7672db599	annoying	2023-01-13 17:00:47 +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