yolov5

Commit Graph

Author	SHA1	Message	Date
Glenn Jocher	a62a45b2dd	prevent testloader caching on --notest	4 years ago
Glenn Jocher	c8e51812a5	hyp evolution force-autoanchor fix	4 years ago
Glenn Jocher	c687d5c129	reorganize train initialization steps	4 years ago
Glenn Jocher	44cdcc7e0b	hyp['anchors'] evolution update	4 years ago
NanoCode012	d8274d0434	Fix results_file not renaming (#903 )	4 years ago
Glenn Jocher	281d78c105	Update train.py (#902 ) * Update train.py with simplified ckpt names * Return default hyps to hyp.scratch.yaml Leave line commented for future use once mystery of best finetuning hyps to apply becomes clearer. * Force test_batch*_pred.jpg replot on final epoch This will allow you to see predictions final testing run after training completes in runs/exp0	4 years ago
Naman Gupta	6f3db5e662	Remove autoanchor and class checks on resumed training (#889 ) * Class frequency not calculated on resuming training Calculation of class frequency is not needed when resuming training. Anchors can still be recalculated whether resuming or not. * Check rank for autoanchor * Update train.py no autoanchor checks on resume Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
Glenn Jocher	f06e2d518c	opt.image_weights bug fix (#885 )	4 years ago
Glenn Jocher	69ff781ca5	opt.img_weights bug fix (#885 )	4 years ago
Glenn Jocher	08e97a2f88	Update hyperparameters to add lrf, anchors	4 years ago
Glenn Jocher	a21bd0687c	Update train.py forward simplification	4 years ago
Glenn Jocher	09402a2174	torch.from_tensor() bug fix	4 years ago
Glenn Jocher	83dc540b1d	remove ema.ema hasattr(ema, 'module') check	4 years ago
Glenn Jocher	4447f4b937	--resume to same runs/exp directory (#765 ) * initial commit * add weight backup dir on resume	4 years ago
NanoCode012	fb4fc8cd02	Fix ema attribute error in DDP mode (#775 ) * Fix ema error in DDP mode * Update train.py Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
Glenn Jocher	ebafd1ead5	single command --resume (#756 ) * single command --resume * else check files, remove TODO * argparse.Namespace() * tensorboard lr * bug fix in get_latest_run()	4 years ago
Glenn Jocher	916d4aad9a	v3.0 Release (#725 ) * initial commit * remove yolov3-spp from test.py study * update study --img range * update mAP * cleanup and speed updates * update README plot	4 years ago
NanoCode012	0892c44bc4	Fix Logging (#719 ) * Add logging setup * Fix fusing layers message * Fix logging does not have end * Add logging * Change logging to use logger * Update yolo.py I tried this in a cloned branch, and everything seems to work fine * Update yolo.py Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
Marc	a925f283a7	max workers for dataloader (#722 )	4 years ago
NanoCode012	4949401a94	Fix redundant outputs via Logging in DDP training (#500 ) * Change print to logging * Clean function set_logging * Add line spacing * Change leftover prints to log * Fix scanning labels output * Fix rank naming * Change leftover print to logging * Reorganized DDP variables * Fix type error * Make quotes consistent * Fix spelling * Clean function call * Add line spacing * Update datasets.py * Update train.py Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
Glenn Jocher	e71fd0ec0b	Model freeze capability (#679 )	4 years ago
Glenn Jocher	8e5c66579b	update train.py remove save_json final_epoch	4 years ago
Glenn Jocher	41523e2c91	Dataset autodownload feature addition (#685 ) * initial commit * move download scripts into data/scripts * new check_dataset() function in general.py * move check_dataset() out of with context * Update general.py * DDP update * Update general.py	4 years ago
NanoCode012	3d8ed0a76b	Fix missing model.stride in DP and DDP mode (#683 )	4 years ago
Glenn Jocher	a0ac5adb7b	Single-source training update (#680 )	4 years ago
Glenn Jocher	3c6e2f7668	Single-source training (#680 ) * Single-source training * Extract hyperparameters into seperate files * weight decay scientific notation yaml reader bug fix * remove import glob * intersect_dicts() implementation * 'or' bug fix * .to(device) bug fix	4 years ago
NanoCode012	d7cfbc47ab	Fix unrecognized local rank argument (#676 )	4 years ago
Glenn Jocher	93684531c6	train.py --logdir argparser addition (#660 ) * train.py --logdir argparser addition * train.py --logdir argparser addition	4 years ago
NanoCode012	886b9841c8	Add Multi-Node support for DDP Training (#504 ) * Add support for multi-node DDP * Remove local_rank confusion * Fix spacing	4 years ago
lorenzomammana	728efa6576	Fix missing imports (#627 ) * Fix missing imports * Update detect.py Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
Glenn Jocher	eb99dff9ef	import random bug fix (#614 )	4 years ago
Jirka Borovec	d5b6416c87	Explicit Imports (#498 ) * expand imports * optimize * miss * fix	4 years ago
Glenn Jocher	f1096b2cf7	hyperparameter evolution update (#566 )	4 years ago
Glenn Jocher	c1a2a7a411	hyperparameter evolution bug fix (#566 )	4 years ago
Glenn Jocher	8074745908	hyperparameter evolution bug fix (#566 )	4 years ago
Glenn Jocher	e32abb5fb9	hyperparameter evolution bug fix (#566 )	4 years ago
Glenn Jocher	8056fe2db8	hyperparameter evolution bug fix (#566 )	4 years ago
Glenn Jocher	127cbeb3f5	hyperparameter expansion to flips, perspective, mixup	4 years ago
Glenn Jocher	bcd452c482	replace random_affine() with random_perspective() Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
Liu Changyu	c020875b17	PyTorch 1.6.0 update with native AMP (#573 ) * PyTorch have Automatic Mixed Precision (AMP) Training. * Fixed the problem of inconsistent code length indentation * Fixed the problem of inconsistent code length indentation * Mixed precision training is turned on by default	4 years ago
Laughing	4e2b9ecc7e	LR --resume repeat bug fix (#565 )	4 years ago
AlexWang1900	a209a32019	Fix bug #541 #542 (#545 ) * fix #541 #542 * Update train.py Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
NanoCode012	7f8471eaeb	--notest bug fix (#518 ) * Fix missing results_file and fi when notest passed * Update train.py reverting previous changes and removing functionality from 'if not opt.notest or final_epoch: # Calculate mAP' loop. Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
Glenn Jocher	9da56b62dd	v2.0 Release (#491 ) Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
Glenn Jocher	5e970d45c4	Update train.py (#462 )	4 years ago
Glenn Jocher	3edc38f603	update train.py gsutil bucket fix (#463 )	4 years ago
Glenn Jocher	776555771f	update train.py gsutil bucket fix (#463 )	4 years ago
Glenn Jocher	b569ed6d6b	pretrained model loading bug fix (#450 ) Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
yzchen	4102fcc9a7	[WIP] Feature/ddp fixed (#401 ) * Squashed commit of the following: commit `d738487089` Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 17:33:38 2020 +0700 Adding world_size Reduce calls to torch.distributed. For use in create_dataloader. commit `e742dd9619` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 15:38:48 2020 +0800 Make SyncBN a choice commit `e90d400438` Merge: 5bf8beb cd90360 Author: yzchen <Chenyzsjtu@gmail.com> Date: Tue Jul 14 15:32:10 2020 +0800 Merge pull request #6 from NanoCode012/patch-5 Update train.py commit `cd9036017e` Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 13:39:29 2020 +0700 Update train.py Remove redundant `opt.` prefix. commit `5bf8bebe88` Merge: c9558a9 a1c8406 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 14:09:51 2020 +0800 Merge branch 'master' of https://github.com/ultralytics/yolov5 into feature/DDP_fixed commit `c9558a9b51` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 13:51:34 2020 +0800 Add device allocation for loss compute commit `4f08c692fb` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 9 11:16:27 2020 +0800 Revert drop_last commit `1dabe33a5a` Merge: a1ce9b1 4b8450b Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 9 11:15:49 2020 +0800 Merge branch 'feature/DDP_fixed' of https://github.com/MagicFrogSJTU/yolov5 into feature/DDP_fixed commit `a1ce9b1e96` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 9 11:15:21 2020 +0800 fix lr warning commit `4b8450b46d` Merge: b9a50ae 02c63ef Author: yzchen <Chenyzsjtu@gmail.com> Date: Wed Jul 8 21:24:24 2020 +0800 Merge pull request #4 from NanoCode012/patch-4 Add drop_last for multi gpu commit `02c63ef81c` Author: NanoCode012 <kevinvong@rocketmail.com> Date: Wed Jul 8 10:08:30 2020 +0700 Add drop_last for multi gpu commit `b9a50aed48` Merge: ec2dc6c 121d90b Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 7 19:48:04 2020 +0800 Merge branch 'master' of https://github.com/ultralytics/yolov5 into feature/DDP_fixed commit `ec2dc6cc56` Merge: d0326e3 82a6182 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 7 19:34:31 2020 +0800 Merge branch 'feature/DDP_fixed' of https://github.com/MagicFrogSJTU/yolov5 into feature/DDP_fixed commit `d0326e398d` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 7 19:31:24 2020 +0800 Add SyncBN commit `82a6182b3a` Merge: 96fa40a 050b2a5 Author: yzchen <Chenyzsjtu@gmail.com> Date: Tue Jul 7 19:21:01 2020 +0800 Merge pull request #1 from NanoCode012/patch-2 Convert BatchNorm to SyncBatchNorm commit `050b2a5a79` Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 7 12:38:14 2020 +0700 Add cleanup for process_group commit `2aa330139f` Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 7 12:07:40 2020 +0700 Remove apex.parallel. Use torch.nn.parallel For future compatibility commit `77c8e27e60` Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 7 01:54:39 2020 +0700 Convert BatchNorm to SyncBatchNorm commit `96fa40a3a9` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Mon Jul 6 21:53:56 2020 +0800 Fix the datset inconsistency problem commit `16e7c269d0` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Mon Jul 6 11:34:03 2020 +0800 Add loss multiplication to preserver the single-process performance commit `e838055630` Merge: 625bb49 3bdea3f Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Fri Jul 3 20:56:30 2020 +0800 Merge branch 'master' of https://github.com/ultralytics/yolov5 into feature/DDP_fixed commit `625bb49f4e` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 2 22:45:15 2020 +0800 DDP established * Squashed commit of the following: commit `94147314e5` Merge: 65157e2 37acbdc Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 16 14:00:17 2020 +0800 Merge branch 'master' of https://github.com/ultralytics/yolov4 into feature/DDP_fixed commit `37acbdc0b6` Author: Glenn Jocher <glenn.jocher@ultralytics.com> Date: Wed Jul 15 20:03:41 2020 -0700 update test.py --save-txt commit `b8c2da4a0d` Author: Glenn Jocher <glenn.jocher@ultralytics.com> Date: Wed Jul 15 20:00:48 2020 -0700 update test.py --save-txt commit `65157e2fc9` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Wed Jul 15 16:44:13 2020 +0800 Revert the README.md removal commit `1c802bfa50` Merge: cd55b44 0f3b8bb Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Wed Jul 15 16:43:38 2020 +0800 Merge branch 'feature/DDP_fixed' of https://github.com/MagicFrogSJTU/yolov5 into feature/DDP_fixed commit `cd55b445c4` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Wed Jul 15 16:42:33 2020 +0800 fix the DDP performance deterioration bug. commit `0f3b8bb1fa` Author: Glenn Jocher <glenn.jocher@ultralytics.com> Date: Wed Jul 15 00:28:53 2020 -0700 Delete README.md commit `f5921ba1e3` Merge: 85ab2f3 bd3fdbb Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Wed Jul 15 11:20:17 2020 +0800 Merge branch 'feature/DDP_fixed' of https://github.com/MagicFrogSJTU/yolov5 into feature/DDP_fixed commit `bd3fdbbf1b` Author: Glenn Jocher <glenn.jocher@ultralytics.com> Date: Tue Jul 14 18:38:20 2020 -0700 Update README.md commit `c1a97a7767` Merge: 2bf86b8 f796708 Author: Glenn Jocher <glenn.jocher@ultralytics.com> Date: Tue Jul 14 18:36:53 2020 -0700 Merge branch 'master' into feature/DDP_fixed commit 2bf86b892fa2fd712f6530903a0d9b8533d7447a Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 22:18:15 2020 +0700 Fixed world_size not found when called from test commit 85ab2f38cdda28b61ad15a3a5a14c3aafb620dc8 Merge: 5a19011 c8357ad Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 22:19:58 2020 +0800 Merge branch 'feature/DDP_fixed' of https://github.com/MagicFrogSJTU/yolov5 into feature/DDP_fixed commit `5a19011949` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 22:19:15 2020 +0800 Add assertion for <=2 gpus DDP commit `c8357ad5b1` Merge: e742dd9 787582f Author: yzchen <Chenyzsjtu@gmail.com> Date: Tue Jul 14 22:10:02 2020 +0800 Merge pull request #8 from MagicFrogSJTU/NanoCode012-patch-1 Modify number of dataloaders' workers commit `787582f972` Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 20:38:58 2020 +0700 Fixed issue with single gpu not having world_size commit `6364892528` Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 19:16:15 2020 +0700 Add assert message for clarification Clarify why assertion was thrown to users commit `69364d6050` Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 17:36:48 2020 +0700 Changed number of workers check commit `d738487089` Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 17:33:38 2020 +0700 Adding world_size Reduce calls to torch.distributed. For use in create_dataloader. commit `e742dd9619` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 15:38:48 2020 +0800 Make SyncBN a choice commit `e90d400438` Merge: 5bf8beb cd90360 Author: yzchen <Chenyzsjtu@gmail.com> Date: Tue Jul 14 15:32:10 2020 +0800 Merge pull request #6 from NanoCode012/patch-5 Update train.py commit `cd9036017e` Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 13:39:29 2020 +0700 Update train.py Remove redundant `opt.` prefix. commit `5bf8bebe88` Merge: c9558a9 a1c8406 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 14:09:51 2020 +0800 Merge branch 'master' of https://github.com/ultralytics/yolov5 into feature/DDP_fixed commit `c9558a9b51` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 13:51:34 2020 +0800 Add device allocation for loss compute commit `4f08c692fb` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 9 11:16:27 2020 +0800 Revert drop_last commit `1dabe33a5a` Merge: a1ce9b1 4b8450b Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 9 11:15:49 2020 +0800 Merge branch 'feature/DDP_fixed' of https://github.com/MagicFrogSJTU/yolov5 into feature/DDP_fixed commit `a1ce9b1e96` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 9 11:15:21 2020 +0800 fix lr warning commit `4b8450b46d` Merge: b9a50ae 02c63ef Author: yzchen <Chenyzsjtu@gmail.com> Date: Wed Jul 8 21:24:24 2020 +0800 Merge pull request #4 from NanoCode012/patch-4 Add drop_last for multi gpu commit `02c63ef81c` Author: NanoCode012 <kevinvong@rocketmail.com> Date: Wed Jul 8 10:08:30 2020 +0700 Add drop_last for multi gpu commit `b9a50aed48` Merge: ec2dc6c 121d90b Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 7 19:48:04 2020 +0800 Merge branch 'master' of https://github.com/ultralytics/yolov5 into feature/DDP_fixed commit `ec2dc6cc56` Merge: d0326e3 82a6182 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 7 19:34:31 2020 +0800 Merge branch 'feature/DDP_fixed' of https://github.com/MagicFrogSJTU/yolov5 into feature/DDP_fixed commit `d0326e398d` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 7 19:31:24 2020 +0800 Add SyncBN commit `82a6182b3a` Merge: 96fa40a 050b2a5 Author: yzchen <Chenyzsjtu@gmail.com> Date: Tue Jul 7 19:21:01 2020 +0800 Merge pull request #1 from NanoCode012/patch-2 Convert BatchNorm to SyncBatchNorm commit `050b2a5a79` Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 7 12:38:14 2020 +0700 Add cleanup for process_group commit `2aa330139f` Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 7 12:07:40 2020 +0700 Remove apex.parallel. Use torch.nn.parallel For future compatibility commit `77c8e27e60` Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 7 01:54:39 2020 +0700 Convert BatchNorm to SyncBatchNorm commit `96fa40a3a9` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Mon Jul 6 21:53:56 2020 +0800 Fix the datset inconsistency problem commit `16e7c269d0` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Mon Jul 6 11:34:03 2020 +0800 Add loss multiplication to preserver the single-process performance commit `e838055630` Merge: 625bb49 3bdea3f Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Fri Jul 3 20:56:30 2020 +0800 Merge branch 'master' of https://github.com/ultralytics/yolov5 into feature/DDP_fixed commit `625bb49f4e` Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 2 22:45:15 2020 +0800 DDP established * Fixed destroy_process_group in DP mode * Update torch_utils.py * Update utils.py Revert build_targets() to current master. * Update datasets.py * Fixed world_size attribute not found Co-authored-by: NanoCode012 <kevinvong@rocketmail.com> Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
Glenn Jocher	07493a715c	update train.py class count assertion #424 Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago

1 2 3 4

155 Commits (96fcde40b883e0d9f337c7fffb38b349f68055e6)