Image Hosting #1

glenn-jocher · 2020-05-26T19:35:23Z

🚀 Feature

Image Placeholder

v6.1

glenn-jocher · 2020-05-26T19:36:42Z

glenn-jocher · 2020-05-27T23:44:46Z

glenn-jocher · 2020-05-31T17:57:13Z

fpn with FP32

panet with FP16

v3.0

v4.0

v3.1

glenn-jocher · 2020-06-09T18:59:50Z

v3.0, start=0, stop=299

Updated coreml conversion to do pixel scaling between 0.0 and 1.0

Master

glenn-jocher · 2020-07-13T20:10:01Z

* Squashed commit of the following: commit d738487 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 e742dd9 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 15:38:48 2020 +0800 Make SyncBN a choice commit e90d400 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 cd90360 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 13:39:29 2020 +0700 Update train.py Remove redundant `opt.` prefix. commit 5bf8beb 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 c9558a9 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 13:51:34 2020 +0800 Add device allocation for loss compute commit 4f08c69 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 9 11:16:27 2020 +0800 Revert drop_last commit 1dabe33 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 a1ce9b1 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 9 11:15:21 2020 +0800 fix lr warning commit 4b8450b 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 02c63ef Author: NanoCode012 <kevinvong@rocketmail.com> Date: Wed Jul 8 10:08:30 2020 +0700 Add drop_last for multi gpu commit b9a50ae 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 ec2dc6c 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 d0326e3 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 7 19:31:24 2020 +0800 Add SyncBN commit 82a6182 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 050b2a5 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 7 12:38:14 2020 +0700 Add cleanup for process_group commit 2aa3301 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 77c8e27 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 7 01:54:39 2020 +0700 Convert BatchNorm to SyncBatchNorm commit 96fa40a Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Mon Jul 6 21:53:56 2020 +0800 Fix the datset inconsistency problem commit 16e7c26 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 e838055 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 625bb49 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 2 22:45:15 2020 +0800 DDP established * Squashed commit of the following: commit 94147314e559a6bdd13cb9de62490d385c27596f 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 37acbdc Author: Glenn Jocher <glenn.jocher@ultralytics.com> Date: Wed Jul 15 20:03:41 2020 -0700 update test.py --save-txt commit b8c2da4 Author: Glenn Jocher <glenn.jocher@ultralytics.com> Date: Wed Jul 15 20:00:48 2020 -0700 update test.py --save-txt commit 65157e2 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Wed Jul 15 16:44:13 2020 +0800 Revert the README.md removal commit 1c802bf 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 cd55b44 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Wed Jul 15 16:42:33 2020 +0800 fix the DDP performance deterioration bug. commit 0f3b8bb Author: Glenn Jocher <glenn.jocher@ultralytics.com> Date: Wed Jul 15 00:28:53 2020 -0700 Delete README.md commit f5921ba 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 bd3fdbb Author: Glenn Jocher <glenn.jocher@ultralytics.com> Date: Tue Jul 14 18:38:20 2020 -0700 Update README.md commit c1a97a7 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 2bf86b8 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 22:18:15 2020 +0700 Fixed world_size not found when called from test commit 85ab2f3 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 5a19011 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 22:19:15 2020 +0800 Add assertion for <=2 gpus DDP commit c8357ad 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 787582f Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 20:38:58 2020 +0700 Fixed issue with single gpu not having world_size commit 6364892 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 69364d6 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 17:36:48 2020 +0700 Changed number of workers check commit d738487 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 e742dd9 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 15:38:48 2020 +0800 Make SyncBN a choice commit e90d400 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 cd90360 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 13:39:29 2020 +0700 Update train.py Remove redundant `opt.` prefix. commit 5bf8beb 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 c9558a9 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 13:51:34 2020 +0800 Add device allocation for loss compute commit 4f08c69 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 9 11:16:27 2020 +0800 Revert drop_last commit 1dabe33 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 a1ce9b1 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 9 11:15:21 2020 +0800 fix lr warning commit 4b8450b 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 02c63ef Author: NanoCode012 <kevinvong@rocketmail.com> Date: Wed Jul 8 10:08:30 2020 +0700 Add drop_last for multi gpu commit b9a50ae 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 ec2dc6c 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 d0326e3 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 7 19:31:24 2020 +0800 Add SyncBN commit 82a6182 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 050b2a5 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 7 12:38:14 2020 +0700 Add cleanup for process_group commit 2aa3301 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 77c8e27 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 7 01:54:39 2020 +0700 Convert BatchNorm to SyncBatchNorm commit 96fa40a Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Mon Jul 6 21:53:56 2020 +0800 Fix the datset inconsistency problem commit 16e7c26 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 e838055 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 625bb49 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>

glenn-jocher · 2021-01-29T20:37:12Z

AWS Tutorial image hosting

glenn-jocher · 2021-04-20T22:43:33Z

centered content

Integrations

Weights & Biases Experiment Logging	Supervise.ly Training Platform

Environments

Google Colab Notebook ^{with free GPU}	Kaggle Notebook ^{with free GPU}	Google Cloud Deep Learning VM	Amazon Deep Learning AMI	Docker Image

Environments Centered

Google Colab Notebook ^{with free GPU}	Kaggle Notebook ^{with free GPU}	Google Cloud Deep Learning VM	Amazon Deep Learning AMI	Docker Image

jeannotes · 2021-06-29T14:23:24Z

@glenn-jocher I asm wondering that in the above pics, eg: https://user-images.githubusercontent.com/26833433/84200349-729f2680-aa5b-11ea-8f9a-604c9e01a658.png

for one single model: yolov5s.yaml, and the x coordinate is inference speed, for one pic, the inference time should be different in different machine, am I mis-understanding, or did you mean that with the same overall-architecture, like yolov5s.yaml, the are still miner differences between them?
hope that you give a hint. thanks

btw, how to reproduce the full results like this picsture?
I know that "python test.py --task study --data coco.yaml --iou 0.7 --weights yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt " may give the results, but how about the difference inference time coordinate, feel confused.

glenn-jocher · 2021-06-29T15:50:05Z

@jeannotes commands to reproduce chart are shown in comments directly below chart. See README.

* Squashed commit of the following: commit d738487 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 e742dd9 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 15:38:48 2020 +0800 Make SyncBN a choice commit e90d400 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 cd90360 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 13:39:29 2020 +0700 Update train.py Remove redundant `opt.` prefix. commit 5bf8beb Merge: c9558a9 880d072 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 c9558a9 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 13:51:34 2020 +0800 Add device allocation for loss compute commit 4f08c69 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 9 11:16:27 2020 +0800 Revert drop_last commit 1dabe33 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 a1ce9b1 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 9 11:15:21 2020 +0800 fix lr warning commit 4b8450b 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 02c63ef Author: NanoCode012 <kevinvong@rocketmail.com> Date: Wed Jul 8 10:08:30 2020 +0700 Add drop_last for multi gpu commit b9a50ae Merge: ec2dc6c 86e7142 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 ec2dc6c 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 d0326e3 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 7 19:31:24 2020 +0800 Add SyncBN commit 82a6182 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 050b2a5 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 7 12:38:14 2020 +0700 Add cleanup for process_group commit 2aa3301 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 77c8e27 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 7 01:54:39 2020 +0700 Convert BatchNorm to SyncBatchNorm commit 96fa40a Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Mon Jul 6 21:53:56 2020 +0800 Fix the datset inconsistency problem commit 16e7c26 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 e838055 Merge: 625bb49 31a9f25 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 625bb49 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 2 22:45:15 2020 +0800 DDP established * Squashed commit of the following: commit 94147314e559a6bdd13cb9de62490d385c27596f Merge: 65157e2 9de5a7a 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 9de5a7a Author: Glenn Jocher <glenn.jocher@ultralytics.com> Date: Wed Jul 15 20:03:41 2020 -0700 update test.py --save-txt commit 825e729 Author: Glenn Jocher <glenn.jocher@ultralytics.com> Date: Wed Jul 15 20:00:48 2020 -0700 update test.py --save-txt commit 65157e2 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Wed Jul 15 16:44:13 2020 +0800 Revert the README.md removal commit 1c802bf 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 cd55b44 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Wed Jul 15 16:42:33 2020 +0800 fix the DDP performance deterioration bug. commit 0f3b8bb Author: Glenn Jocher <glenn.jocher@ultralytics.com> Date: Wed Jul 15 00:28:53 2020 -0700 Delete README.md commit f5921ba 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 bd3fdbb Author: Glenn Jocher <glenn.jocher@ultralytics.com> Date: Tue Jul 14 18:38:20 2020 -0700 Update README.md commit c1a97a7 Merge: 2bf86b8 7d73bfb Author: Glenn Jocher <glenn.jocher@ultralytics.com> Date: Tue Jul 14 18:36:53 2020 -0700 Merge branch 'master' into feature/DDP_fixed commit 2bf86b8 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 22:18:15 2020 +0700 Fixed world_size not found when called from test commit 85ab2f3 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 5a19011 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 22:19:15 2020 +0800 Add assertion for <=2 gpus DDP commit c8357ad Merge: e742dd9 787582f Author: yzchen <Chenyzsjtu@gmail.com> Date: Tue Jul 14 22:10:02 2020 +0800 Merge pull request ultralytics#8 from MagicFrogSJTU/NanoCode012-patch-1 Modify number of dataloaders' workers commit 787582f Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 20:38:58 2020 +0700 Fixed issue with single gpu not having world_size commit 6364892 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 69364d6 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 17:36:48 2020 +0700 Changed number of workers check commit d738487 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 e742dd9 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 15:38:48 2020 +0800 Make SyncBN a choice commit e90d400 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 cd90360 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 14 13:39:29 2020 +0700 Update train.py Remove redundant `opt.` prefix. commit 5bf8beb Merge: c9558a9 880d072 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 c9558a9 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 14 13:51:34 2020 +0800 Add device allocation for loss compute commit 4f08c69 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 9 11:16:27 2020 +0800 Revert drop_last commit 1dabe33 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 a1ce9b1 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Thu Jul 9 11:15:21 2020 +0800 fix lr warning commit 4b8450b 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 02c63ef Author: NanoCode012 <kevinvong@rocketmail.com> Date: Wed Jul 8 10:08:30 2020 +0700 Add drop_last for multi gpu commit b9a50ae Merge: ec2dc6c 86e7142 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 ec2dc6c 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 d0326e3 Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Tue Jul 7 19:31:24 2020 +0800 Add SyncBN commit 82a6182 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 050b2a5 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 7 12:38:14 2020 +0700 Add cleanup for process_group commit 2aa3301 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 77c8e27 Author: NanoCode012 <kevinvong@rocketmail.com> Date: Tue Jul 7 01:54:39 2020 +0700 Convert BatchNorm to SyncBatchNorm commit 96fa40a Author: yizhi.chen <chenyzsjtu@outlook.com> Date: Mon Jul 6 21:53:56 2020 +0800 Fix the datset inconsistency problem commit 16e7c26 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 e838055 Merge: 625bb49 31a9f25 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 625bb49 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>

add test yolov5 weights and image

3LC Yolo Integration feature patch ultralytics#1

glenn-jocher added the enhancement New feature or request label May 26, 2020

glenn-jocher closed this as completed May 27, 2020

glenn-jocher changed the title ~~Image Placeholder~~ Image Hosting Jun 9, 2020

matinhosseiny mentioned this issue Jun 23, 2020

RuntimeError: cuDNN error: CUDNN_STATUS_BAD_PARAM #185

Closed

DLLXW mentioned this issue Jul 3, 2020

RuntimeError: CUDA error: no kernel image is available for execution on the device (nms_cuda at /tmp/pip-req-build-9d9zypi6/torchvision/csrc/cuda/nms_cuda.cu:127) #281

Closed

rcg12387 mentioned this issue Jul 3, 2020

TFLite, ONNX, CoreML, TensorRT Export #251

Open

glenn-jocher pushed a commit that referenced this issue Jul 8, 2020

Merge pull request #1 from dlawrences/dev/coreml_convert_pxscaling

7c4d3cf

Updated coreml conversion to do pixel scaling between 0.0 and 1.0

glenn-jocher pushed a commit that referenced this issue Jul 10, 2020

Merge pull request #1 from ultralytics/master

41ab1b2

Master

glenn-jocher mentioned this issue Jul 14, 2020

Pseudo-labeling with Yolov5 (similar to darknet) for Active Learning #404

Closed

govindamagrawal mentioned this issue Jul 24, 2020

Not able to run torchscript model in c++ #505

Closed

glenn-jocher self-assigned this Nov 2, 2020

zhepherd mentioned this issue Nov 5, 2020

yolov5l to libtorch error #1293

Closed

forallsunday mentioned this issue Nov 19, 2020

Can't run with GPU, but worked with CPU #1448

Closed

Roshnee mentioned this issue Nov 19, 2020

Unable to convert .onnx to tflite #1453

Closed

wuzuiyuzui mentioned this issue Nov 27, 2020

RuntimeError: cuDNN error: CUDNN_STATUS_INTERNAL_ERROR #1546

Closed

glenn-jocher mentioned this issue Dec 20, 2020

Input channel yaml['ch'] addition #1741

Merged

jerryWTMH mentioned this issue Dec 22, 2020

RuntimeError: CUDA error: unspecified launch failure #1752

Closed

glenn-jocher mentioned this issue Jan 27, 2021

W&B log epoch #1946

Merged

RobinBram mentioned this issue Jan 29, 2021

Can't reproduce the outputs from the detect.py file on images/bus or images/zidane locally #2080

Closed

dcboy mentioned this issue Feb 3, 2021

RuntimeError: DataLoader worker #1908

Closed

glenn-jocher mentioned this issue Feb 18, 2021

Hyperparameter Evolution #607

Open

glenn-jocher mentioned this issue Mar 11, 2021

Add ASFF (three fuse feature layers) int the Head for V5(s,m,l,x) #2348

Closed

ultralytics deleted a comment from github-actions bot Apr 11, 2021

alicera mentioned this issue Jun 23, 2021

different gpus to train #3736

Closed

coallar mentioned this issue Sep 18, 2021

CUDA error: the launch timed out and was terminated #4851

Closed

leandervaneekelen mentioned this issue Dec 9, 2021

Loss masking to deal with sparsely labeled data #5917

Closed

1 task

GriffinBoris mentioned this issue Jan 6, 2022

ImportError: cannot import name 'DetectMultiBackend' . #6093

Closed

2 tasks

johnng0805 added a commit to johnng0805/yolov5 that referenced this issue Jun 17, 2022

Demo ultralytics#1

d070152

glenn-jocher mentioned this issue Oct 12, 2022

masks2segments function does not always work correctly #9784

Closed

2 tasks

JeremyCraigMartinez mentioned this issue Oct 22, 2022

TypeError: update_output_model() got an unexpected keyword argument 'auto_delete_file' #9889

Closed

2 tasks

cswingley mentioned this issue Nov 15, 2022

CPU training works OK. GPU training always loss=nan and mAP50=0. GPU detection OK. #9709

Closed

2 tasks

manole-alexandru referenced this issue in manole-alexandru/yolov5-uolo Mar 10, 2023

Print #1

3015f5d

manole-alexandru referenced this issue in manole-alexandru/yolov5-uolo Mar 14, 2023

pbar error fix attempt #1

336b3ee

manole-alexandru referenced this issue in manole-alexandru/yolov5-uolo Mar 20, 2023

readded seg objective #1

ba46faf

cool112624 mentioned this issue May 16, 2023

DDP training with multiple gpu using wsl #11519

Closed

1 task

thiendt2k1 mentioned this issue Jul 7, 2023

(Possibly) Cuda version conflict when training classifcation on custom dataset on Colab #11833

Closed

1 task

edehino mentioned this issue Jul 14, 2023

How to prevent model from mistaking the background as an object? #11861

Closed

1 task

RosieYC pushed a commit to RosieYC/yolov5 that referenced this issue Sep 15, 2023

Merge pull request ultralytics#1 from LeBron-Jian/james

3d7fc08

add test yolov5 weights and image

jcluo1994 mentioned this issue Oct 10, 2023

Using multi-GPU training reports errors #12213

Closed

1 task

SohaibKtb mentioned this issue Oct 20, 2023

segmentation fault #1620

Closed

3lcai added a commit to 3lc-ai/yolov5 that referenced this issue Dec 7, 2023

3LC Yolo Integration feature patch ultralytics#1

f9fea73

3lcai mentioned this issue Dec 7, 2023

3LC Yolo Integration feature patch #1 3lc-ai/yolov5#7

Merged

gudbrandtandberg added a commit to 3lc-ai/yolov5 that referenced this issue Dec 8, 2023

Merge pull request #7 from 3lc-ai/update-from-build-19625

b68b4fa

3LC Yolo Integration feature patch ultralytics#1

james-imi mentioned this issue Jan 31, 2024

Comet ML doesn't log on segment/train.py #12693

Closed

2 tasks

Heaven0612 mentioned this issue Jun 26, 2024

YOLOv5 receptive range size #13127

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Image Hosting #1

Image Hosting #1

glenn-jocher commented May 26, 2020 •

edited

Loading

glenn-jocher commented May 26, 2020 •

edited

Loading

glenn-jocher commented May 27, 2020 •

edited

Loading

glenn-jocher commented May 31, 2020 •

edited

Loading

glenn-jocher commented Jun 9, 2020 •

edited

Loading

glenn-jocher commented Jul 13, 2020 •

edited

Loading

glenn-jocher commented Jan 29, 2021 •

edited

Loading

glenn-jocher commented Apr 20, 2021 •

edited

Loading

jeannotes commented Jun 29, 2021

glenn-jocher commented Jun 29, 2021

Image Hosting #1

Image Hosting #1

Comments

glenn-jocher commented May 26, 2020 • edited Loading

🚀 Feature

v6.1

glenn-jocher commented May 26, 2020 • edited Loading

glenn-jocher commented May 27, 2020 • edited Loading

glenn-jocher commented May 31, 2020 • edited Loading

glenn-jocher commented Jun 9, 2020 • edited Loading

glenn-jocher commented Jul 13, 2020 • edited Loading

glenn-jocher commented Jan 29, 2021 • edited Loading

glenn-jocher commented Apr 20, 2021 • edited Loading

Integrations

Environments

Environments Centered

jeannotes commented Jun 29, 2021

glenn-jocher commented Jun 29, 2021

glenn-jocher commented May 26, 2020 •

edited

Loading

glenn-jocher commented May 26, 2020 •

edited

Loading

glenn-jocher commented May 27, 2020 •

edited

Loading

glenn-jocher commented May 31, 2020 •

edited

Loading

glenn-jocher commented Jun 9, 2020 •

edited

Loading

glenn-jocher commented Jul 13, 2020 •

edited

Loading

glenn-jocher commented Jan 29, 2021 •

edited

Loading

glenn-jocher commented Apr 20, 2021 •

edited

Loading