509 commits

Author	SHA1	Message	Date
Starbeamrainbowlabs	f0a2e7c450	dlr: print values of new env vars	2023-05-04 19:42:40 +01:00
Starbeamrainbowlabs	8593999eb6	dlr: add JIT_COMPILE	2023-05-04 18:22:18 +01:00
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