yolov5

Commit Graph

作者	SHA1	備註	提交日期
Glenn Jocher	03489aaafb	comment tb_writer.add_hparams(hyp, {})	4 年之前
Glenn Jocher	120d40c06a	Update train.py This updates the PR to a one-liner to minimize additions. Perhaps we can include opt in the future but let's start with this for now.	4 年之前
Janko Ondras	38acc5f3c5	Fix img_size naming in hyperparameters logging	4 年之前
Glenn Jocher	a1c8406af3	EMA and non_blocking=True	4 年之前
Glenn Jocher	140d84cca1	comment updates	4 年之前
Janko Ondras	e558963244	Log hyperparameters in tensorboard Log both hyperparameters and command line options in tensorboard.	4 年之前
Glenn Jocher	01a73ec08e	multi-gpu ckpt filesize bug fix #253	4 年之前
Glenn Jocher	a586751904	multi-gpu ckpt filesize bug fix #253	4 年之前
Glenn Jocher	5de4e25d68	update tensorboard metric	4 年之前
Glenn Jocher	98fc483abc	train.py results.txt to bucket bug fix	4 年之前
Glenn Jocher	1c13e67b33	evolution bug fix #346	4 年之前
Laughing	51a161d9e1	Update train.py	4 年之前
Glenn Jocher	e16e9e43e1	new nc=len(names) check	4 年之前
Glenn Jocher	cb527d3af9	new nc=len(names) check	4 年之前
Glenn Jocher	603ea0bfdc	update log_dir to runs/exp #107	4 年之前
Glenn Jocher	72d5b58b9a	disable LR plot to suppress warning message	4 年之前
Glenn Jocher	24c5a941f0	--resume EMA fix #292	4 年之前
Alex Stoken	9d631408a2	Move hyp and opt yaml save to top of train() Fixes bug where scaled values were saved in hyp.yaml, which would cause continuity issues with --resume	4 年之前
Glenn Jocher	bf6f41567a	hyperparameter printout update	4 年之前
Glenn Jocher	6b134d93c5	Update train.py	4 年之前
Glenn Jocher	16f6834486	update train.py and experimental.py	4 年之前
Alex Stoken	52bac22f09	Add in --resume functionality with option to specify path or to get most recent run	4 年之前
Laughing	956511dafd	fix LR bug	4 年之前
Glenn Jocher	bb3c346916	model.yaml nc inherited from dataset.yaml	4 年之前
Glenn Jocher	df224a0d8f	EMA bug fix #279	4 年之前
Glenn Jocher	3bdea3f697	strip_optimizer() bug fix #253	4 年之前
Glenn Jocher	597ed4ce63	Update train.py	4 年之前
Glenn Jocher	9705c15da1	Update train.py	4 年之前
ChristopherSTAN	a8d17ce712	Update train.py	4 年之前
Glenn Jocher	13f69777a6	typo fix	4 年之前
yxNONG	1aa2b67933	Update train.py	4 年之前
Glenn Jocher	86784cfdbf	--resume bug fix #252	4 年之前
Glenn Jocher	ad4c22cbfe	--resume bug fix #187	4 年之前
Glenn Jocher	3b16c865f0	assert --epochs	4 年之前
yxNONG	cdb9bde181	Unify the check point of single and multi GPU save the model.hyp etc to checkpoint when use multi GPU training	4 年之前
Glenn Jocher	b203c9b7ff	update train.py incompatible model message fix #222	4 年之前
Glenn Jocher	37e13f8846	update mosaic border	4 年之前
Glenn Jocher	22fb2b0c25	refactor dataloader	4 年之前
Glenn Jocher	256a3e89d2	small dataset bug fix #140	4 年之前
Glenn Jocher	b50fdf16af	model.names multi-GPU bug fix #94	4 年之前
Alex Stoken	de191655e4	Fix yaml saving (don't sort keys), reorder --opt keys, bug fix hyp dict accessor	4 年之前
Alex Stoken	2d396bea00	Fix bug in --help from percent sign in help string	4 年之前
Glenn Jocher	b8557f87e3	add stride to datasets.py	4 年之前
Alex Stoken	611aacf1bf	Turn opt into dictionary before sending it to yaml	4 年之前
Alex Stoken	bc4ef4861b	Default optimizer SGD	4 年之前
Alex Stoken	7abf202cad	Mode all optimizer settings to 'hyp.yaml', integrate proper momentum with Adam optimizer	4 年之前
Alex Stoken	7edbf6570e	Fix help message for cfg files	4 年之前
Alex Stoken	d64ad0fbf3	Remove --resume functionality and related checks/logic.	4 年之前
Glenn Jocher	6c1b87a42e	update google_utils import	4 年之前
Glenn Jocher	1f1917ef56	remove fast, add merge	4 年之前

1 2

93 次程式碼提交 (1ce686edfc095a313c0ceb230fd28f9c868a5345)