36 Commits (2d396bea00df15dc2b27727f9e3ef340df71f1de)

Author SHA1 Message Date
  Alex Stoken 2d396bea00 Fix bug in --help from percent sign in help string 4 years ago
  Alex Stoken 611aacf1bf Turn opt into dictionary before sending it to yaml 4 years ago
  Alex Stoken bc4ef4861b Default optimizer SGD 4 years ago
  Alex Stoken 7abf202cad Mode all optimizer settings to 'hyp.yaml', integrate proper momentum with Adam optimizer 4 years ago
  Alex Stoken 7edbf6570e Fix help message for cfg files 4 years ago
  Alex Stoken d64ad0fbf3 Remove --resume functionality and related checks/logic. 4 years ago
  Alex Stoken e572bb0803 Add plot_results save location to log_dir 4 years ago
  Alex Stoken c8152c81a6 Syntax fixes 4 years ago
  Alex Stoken 9b7386f603 Add save_dir arg to test.test, use arg as location for saving batch jpgs 4 years ago
  Alex Stoken 945307beba Add save_dir to plot_lr_scheduler and plot_labels 4 years ago
  Alex Stoken 3b2b330872 Move results.txt from weights/ to log_dir 4 years ago
  Alex Stoken ade023cff2 Fix hyp file read in and dict update. 4 years ago
  Alex Stoken 5f2eeba233 remove old print statements 4 years ago
  Alex Stoken 333f678b37 add update default hyp dict with provided yaml 4 years ago
  Alex Stoken a448c3bcd7 add logic for resuming and getting hyp for resume run 4 years ago
  Alex Stoken 25e51bcec7 add util function to get most recent last.pt file 4 years ago
  Alex Stoken 490f1e7b9c add save_dir arg to plot_lr_scheduler, default to current dir. 4 years ago
  Alex Stoken 4418809cf5 change weights dir (wdir) to be unique to each run, under log_dir 4 years ago
  Alex Stoken d9f446cd81 add save yaml of opt and hyp to tensorboard log_dir in train() 4 years ago
  Alex Stoken a85e6d0fc0 add parser arg for hyp yaml file 4 years ago
  Glenn Jocher 8b26e89006 AutoAnchor bug fix #72 4 years ago
  Glenn Jocher bdd9fee841 update fast mode 4 years ago
  Glenn Jocher 1c0b6236e3 update fast mode 4 years ago
  Glenn Jocher 915b1481fc default check_git_status() to True 4 years ago
  Glenn Jocher 14523bb030 FP16 to FP32 ckpt load 4 years ago
  Glenn Jocher c5966abba8 glob search bug fix #77 4 years ago
  Glenn Jocher 31f3310029 assert best possible recall > 0.9 before training 4 years ago
  Lauritzen Kasper Primdal c3d4d321d3 Ensures weights/ dir exists 4 years ago
  Glenn Jocher 099e6f5ebd --img-size stride-multiple verification 4 years ago
  Glenn Jocher 22d6088205 speed-reproducibility fix #17 4 years ago
  Glenn Jocher 55ca5c74d2 multi-scale fix #16 4 years ago
  Glenn Jocher 7c2832cd49 assert equal model and dataset classes 4 years ago
  Glenn Jocher 11121e39ed updates 4 years ago
  Glenn Jocher eb97b2e413 NMS fast mode 4 years ago
  Glenn Jocher ce36905358 updates 4 years ago
  Glenn Jocher 1e84a23f38 initial commit 4 years ago