93 Commits

Author	SHA1	Message	Date
Glenn Jocher	c3d3e6b776	Update test.py	2020-07-08 16:27:52 -07:00
Glenn Jocher	e8cf24b6c8	Initial model ensemble capability #318	2020-07-07 15:40:50 -07:00
Alex Stoken	5ac517b22a	Remove duplicate verbose arg in test.py	2020-07-07 10:09:53 -05:00
Alex Stoken	f517ba81c7	Merge branch 'master' into advanced_logging	2020-07-06 16:52:11 -05:00
Glenn Jocher	6b95d6d2c0	.to(device) bug fix	2020-07-05 23:37:36 -07:00
Glenn Jocher	a62333e808	test.py .fuse() update	2020-07-05 23:27:03 -07:00
Glenn Jocher	04bdbe4104	fuse update	2020-07-05 23:16:50 -07:00
Glenn Jocher	a9dc0c2c29	update check_img_size() for model strides	2020-06-30 15:25:38 -07:00
Alex Stoken	e18e6811dc	Merge branch 'master' into advanced_logging	2020-06-27 10:13:03 -05:00
Glenn Jocher	22fb2b0c25	refactor dataloader	2020-06-26 18:56:13 -07:00
Glenn Jocher	e670a3353b	update test.py for FP16 testing during training	2020-06-25 15:09:04 -07:00
Glenn Jocher	227aa735dc	updates	2020-06-24 13:20:14 -07:00
Glenn Jocher	b8557f87e3	add stride to datasets.py	2020-06-24 13:02:27 -07:00
Glenn Jocher	a63e1c9b3c	study update	2020-06-22 23:23:50 -07:00
Glenn Jocher	db898131f9	study update	2020-06-22 23:07:22 -07:00
Glenn Jocher	6c1b87a42e	update google_utils import	2020-06-22 23:00:23 -07:00
Glenn Jocher	1f1917ef56	remove fast, add merge	2020-06-21 13:37:11 -07:00
Alex Stoken	9b7386f603	Add save_dir arg to test.test, use arg as location for saving batch jpgs	2020-06-17 16:08:46 -05:00
Glenn Jocher	2daa412575	train with multi-gpu half test bug fix #99	2020-06-16 16:28:25 -07:00
Glenn Jocher	d1e5716610	train with multi-gpu half test bug fix #99	2020-06-16 16:22:58 -07:00
Glenn Jocher	72d06147b2	Multi-GPU disabled in test.py	2020-06-16 14:42:30 -07:00
Glenn Jocher	7c6fd4d670	--verbose bug fix #84	2020-06-16 10:22:22 -07:00
Glenn Jocher	db2c3acd3a	updated testing settings, rebalanced towards FP16 latency	2020-06-15 16:55:57 -07:00
Glenn Jocher	0b514daced	FP16 test loss bug fix	2020-06-15 15:26:29 -07:00
Glenn Jocher	a1748a8d6e	test during training default to FP16	2020-06-15 15:20:27 -07:00
Glenn Jocher	76ca367a01	FP16 to FP32 ckpt load	2020-06-15 13:32:45 -07:00
Glenn Jocher	c5966abba8	glob search bug fix #77	2020-06-15 12:08:57 -07:00
Glenn Jocher	e7c24e04ac	half() fix #66	2020-06-15 00:43:57 -07:00
Glenn Jocher	111994956e	switch default inference to FP16 on GPU	2020-06-14 19:25:39 -07:00
Glenn Jocher	157aff2854	FP16 inference fix	2020-06-14 18:45:20 -07:00
Glenn Jocher	260b1729f0	FP16 inference update	2020-06-14 18:32:29 -07:00
Glenn Jocher	099e6f5ebd	--img-size stride-multiple verification	2020-06-12 22:10:46 -07:00
Glenn Jocher	d187459dd4	study changes	2020-06-08 10:42:33 -07:00
Glenn Jocher	546f973562	model fuse	2020-06-07 14:47:48 -07:00
Glenn Jocher	208493d959	updates	2020-06-05 16:34:05 -07:00
Glenn Jocher	dbdee3a4a3	multi-gpu test bug fix #15	2020-06-04 15:23:03 -07:00
Glenn Jocher	ba9ab663a2	model.names for dataParallel	2020-06-04 13:30:14 -07:00
Glenn Jocher	2a0aff685a	dataset padding mode	2020-06-03 13:55:33 -07:00
Glenn Jocher	eb97b2e413	NMS fast mode	2020-06-03 13:02:59 -07:00
Glenn Jocher	ee8988b8a2	datasets.py self.batch_shapes fix	2020-06-01 18:11:18 -07:00
Glenn Jocher	7960c4c5d8	updates	2020-05-30 09:28:11 -07:00
Glenn Jocher	ce36905358	updates	2020-05-30 00:12:45 -07:00
Glenn Jocher	1e84a23f38	initial commit	2020-05-29 17:04:54 -07:00