Commit Graph

126 Commits (1f92422e206405972e7e9766b47dcf044c9a784e)

Author SHA1 Message Date
Alex Stoken 9d631408a2
Move hyp and opt yaml save to top of train() 5 years ago
Glenn Jocher bf6f41567a hyperparameter printout update 5 years ago
Glenn Jocher dc5e18390a
Merge branch 'master' into advanced_logging 5 years ago
Glenn Jocher 6b134d93c5
Update train.py 5 years ago
Glenn Jocher 16f6834486 update train.py and experimental.py 5 years ago
Alex Stoken 52bac22f09 Add in --resume functionality with option to specify path or to get most recent run 5 years ago
Alex Stoken f517ba81c7
Merge branch 'master' into advanced_logging 5 years ago
Laughing 956511dafd
fix LR bug 5 years ago
Glenn Jocher bb3c346916 model.yaml nc inherited from dataset.yaml 5 years ago
Glenn Jocher df224a0d8f EMA bug fix 5 years ago
Glenn Jocher 3bdea3f697 strip_optimizer() bug fix 5 years ago
Glenn Jocher e02a189a3a
Merge pull request from yxNONG/patch-2 5 years ago
Glenn Jocher 597ed4ce63
Update train.py 5 years ago
Glenn Jocher 13f69777a6 typo fix 5 years ago
yxNONG 1aa2b67933
Update train.py 5 years ago
Glenn Jocher 86784cfdbf --resume bug fix 5 years ago
Glenn Jocher ad4c22cbfe --resume bug fix 5 years ago
Glenn Jocher 3b16c865f0 assert --epochs 5 years ago
yxNONG cdb9bde181
Unify the check point of single and multi GPU 5 years ago
Glenn Jocher b203c9b7ff update train.py incompatible model message fix 5 years ago
Glenn Jocher 37e13f8846 update mosaic border 5 years ago
Alex Stoken e18e6811dc
Merge branch 'master' into advanced_logging 5 years ago
Glenn Jocher 22fb2b0c25 refactor dataloader 5 years ago
Glenn Jocher 256a3e89d2 small dataset bug fix 5 years ago
Glenn Jocher b50fdf16af model.names multi-GPU bug fix 5 years ago
Alex Stoken de191655e4 Fix yaml saving (don't sort keys), reorder --opt keys, bug fix hyp dict accessor 5 years ago
Alex Stoken 2d396bea00 Fix bug in --help from percent sign in help string 5 years ago
Glenn Jocher b8557f87e3 add stride to datasets.py 5 years ago
Alex Stoken 611aacf1bf Turn opt into dictionary before sending it to yaml 5 years ago
Alex Stoken bc4ef4861b Default optimizer SGD 5 years ago
Alex Stoken 7abf202cad Mode all optimizer settings to 'hyp.yaml', integrate proper momentum with Adam optimizer 5 years ago
Alex Stoken 7edbf6570e Fix help message for cfg files 5 years ago
Alex Stoken d64ad0fbf3 Remove --resume functionality and related checks/logic. 5 years ago
Glenn Jocher 6c1b87a42e update google_utils import 5 years ago
Glenn Jocher 1f1917ef56 remove fast, add merge 5 years ago
Alex Stoken e572bb0803 Add plot_results save location to log_dir 5 years ago
Lornatang 899f1d4bde Fix DDP bug in single process multiple device use cases 5 years ago
Glenn Jocher cdf1eac9f7
Merge pull request from Lornatang/fix-reference-bugs 5 years ago
Glenn Jocher cce95e744d backbone as FP16, save default to FP32 5 years ago
Glenn Jocher d9b64c27c2 save ckpt in FP16 5 years ago
Glenn Jocher 9fdb0fbacf AutoAnchor bug fix # 117 5 years ago
Alex Stoken c8152c81a6 Syntax fixes 5 years ago
Alex Stoken 9b7386f603 Add save_dir arg to test.test, use arg as location for saving batch jpgs 5 years ago
Alex Stoken 945307beba Add save_dir to plot_lr_scheduler and plot_labels 5 years ago
Alex Stoken 3b2b330872 Move results.txt from weights/ to log_dir 5 years ago
Alex Stoken ade023cff2 Fix hyp file read in and dict update. 5 years ago
Lornatang 2368603484 fix refrence bug 5 years ago
Glenn Jocher 8db51c7002 tb_writer bug fix 5 years ago
Alex Stoken 5f2eeba233 remove old print statements 5 years ago
Glenn Jocher afe1df385b dist.destroy_process_group() bug fix 5 years ago
Alex Stoken 333f678b37 add update default hyp dict with provided yaml 5 years ago
Alex Stoken a448c3bcd7 add logic for resuming and getting hyp for resume run 5 years ago
Alex Stoken 25e51bcec7 add util function to get most recent last.pt file 5 years ago
Alex Stoken 490f1e7b9c add save_dir arg to plot_lr_scheduler, default to current dir. 5 years ago
Alex Stoken 4418809cf5 change weights dir (wdir) to be unique to each run, under log_dir 5 years ago
Alex Stoken d9f446cd81 add save yaml of opt and hyp to tensorboard log_dir in train() 5 years ago
Alex Stoken a85e6d0fc0 add parser arg for hyp yaml file 5 years ago
Glenn Jocher 5a50491fa1 check_anchors bug fix 5 years ago
Glenn Jocher 05b8ee5ca4 check_anchors() bug fix 5 years ago
Glenn Jocher ec81c7b5f2 check_anchors() bug fix 5 years ago
Glenn Jocher 8b26e89006 AutoAnchor bug fix 5 years ago
Glenn Jocher bdd9fee841 update fast mode 5 years ago
Glenn Jocher 1c0b6236e3 update fast mode 5 years ago
Glenn Jocher 915b1481fc default check_git_status() to True 5 years ago
Glenn Jocher 14523bb030 FP16 to FP32 ckpt load 5 years ago
Glenn Jocher c5966abba8 glob search bug fix 5 years ago
Glenn Jocher 31f3310029 assert best possible recall > 0.9 before training 5 years ago
Lauritzen Kasper Primdal c3d4d321d3 Ensures weights/ dir exists 5 years ago
Glenn Jocher 099e6f5ebd --img-size stride-multiple verification 5 years ago
Glenn Jocher 22d6088205 speed-reproducibility fix 5 years ago
Glenn Jocher 55ca5c74d2 multi-scale fix 5 years ago
Glenn Jocher 7c2832cd49 assert equal model and dataset classes 5 years ago
Glenn Jocher 11121e39ed updates 5 years ago
Glenn Jocher eb97b2e413 NMS fast mode 5 years ago
Glenn Jocher ce36905358 updates 5 years ago
Glenn Jocher 1e84a23f38 initial commit 5 years ago