e77c77f580
Add check_requirements() ( #1853 )
...
* Add check_requirements()
* add import
* parameterize filename
* add to detect, test
2021-01-06 16:35:40 -08:00
69be8e738f
YOLOv5 v4.0 Release ( #1837 )
...
* Update C3 module
* Update C3 module
* Update C3 module
* Update C3 module
* update
* update
* update
* update
* update
* update
* update
* update
* update
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* update
* update
* update
* update
* updates
* updates
* updates
* updates
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update datasets
* update
* update
* update
* update attempt_downlaod()
* merge
* merge
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* parameterize eps
* comments
* gs-multiple
* update
* max_nms implemented
* Create one_cycle() function
* update
* update
* update
* update
* update
* update
* update
* update study.png
* update study.png
* Update datasets.py
2021-01-04 19:54:09 -08:00
0e341c5660
Create one_cycle() function ( #1836 )
2021-01-04 15:49:08 -08:00
7180b22e2d
DDP Multi-GPU --resume bug fix ( #1810 )
2020-12-30 12:40:45 -08:00
685d601308
Increase plot_labels() speed ( #1736 )
2020-12-18 18:05:38 -08:00
7e161d9774
Single class train update ( #1719 )
2020-12-17 12:02:03 -08:00
c923fbff90
W&B artifacts feature addition ( #1712 )
...
* Log artifacts
* cleanup
2020-12-16 17:52:12 -08:00
8bc0027afc
Update loss criteria constructor ( #1711 )
2020-12-16 08:39:35 -08:00
7947c86b57
Update COCO train postprocessing ( #1702 )
2020-12-15 21:50:28 -08:00
791dadb51c
Pycocotools best.pt after COCO train ( #1616 )
...
* Pycocotools best.pt after COCO train
* cleanup
2020-12-06 14:58:33 +01:00
b6ed1104a6
Daemon thread plotting ( #1561 )
...
* Daemon thread plotting
* remove process_batch
* plot after print
2020-11-30 16:44:14 +01:00
9728e2b8ae
--image_weights bug fix ( #1524 )
2020-11-26 11:49:01 +01:00
bde5d9aaaa
Update caching ( #1496 )
2020-11-24 16:23:00 +01:00
0822cda781
Update caching ( #1496 )
2020-11-24 16:22:02 +01:00
0a3ff71ae0
Confusion matrix ( #1474 )
...
* initial commit
* add plotting
* matrix to cpu
* bug fix
* update plot
* update plot
* update plot
* update plot
* update plot
* update plot
* update plot
* update plot
* update plot
* update plot
* update plot
* update plot
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* seaborn pandas to requirements.txt
* seaborn pandas to requirements.txt
* update wandb plotting
* remove pandas
* if plots
* if plots
* if plots
* if plots
* if plots
* initial commit
* add plotting
* matrix to cpu
* bug fix
* update plot
* update plot
* update plot
* update plot
* update plot
* update plot
* update plot
* update plot
* update plot
* update plot
* update plot
* update plot
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* cleanup
* seaborn pandas to requirements.txt
* seaborn pandas to requirements.txt
* update wandb plotting
* remove pandas
* if plots
* if plots
* if plots
* if plots
* if plots
* Cat apriori to autolabels
* cleanup
2020-11-23 15:27:14 +01:00
9ef4760b74
Rename precision_recall_curve.png bug fix ( #1431 )
...
* fix error in train.py line 400, changed precision-recall_curve.png to precision_recall_curve.png and fix error in test.py of {wandb.init() before wandb.log()} by importing wand and initializing it before wand.log()
* Update test.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-11-17 23:47:27 +01:00
9c91aeae10
W&B logging add hyperparameters ( #1399 )
...
* W&B logging add hyperparameters
* hyp bug fix and image logging updates
* if plots and wandb:
* cleanup
* wandb/ gitignore add
* cleanup 2
* cleanup 3
* move wandb import to top of file
* wandb evolve
* update import
* wandb.run.finish()
* default anchors: 3
2020-11-16 13:35:34 +01:00
0c26c4e831
Increase pycocotools robustness ( #1396 )
2020-11-14 13:53:58 +01:00
fe341fa44d
Utils reorganization ( #1392 )
...
* Utils reorganization
* Add new utils files
* cleanup
* simplify
* reduce datasets.py
* remove evolve.sh
* loadWebcam cleanup
2020-11-14 11:50:32 +01:00
379396e896
Yaml constructor posixpath --resume bug fix ( #1390 )
...
* resume fix for yaml constructor posixpath error
* fix update
* remove weights/ dir backup
2020-11-13 19:03:02 +01:00
c4addd7761
Unified '/project/name' results saving ( #1377 )
...
* Project/name update
* Update ci-testing.yml
* address project with path separator failure mode
* Project/name update
* address project with path separator failure mode
* Update ci-testing.yml
* detect.py default --name bug fix
* missing rstrip PR
* train/exp0 to train/exp
2020-11-12 23:37:46 +01:00
ce3872f86c
W&B evolution bug fix ( #1373 )
2020-11-12 12:55:52 +01:00
1c8464e199
Use pathlib instead of low-level module ( #1329 )
...
* Use pathlib instead of low-level module
* Use pathlib instead of low-level module
* Update detect.py
* Update test.py
* reformat
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-11-10 13:01:19 +01:00
4821d076e2
Increment train, test, detect runs/ ( #1322 )
...
* Increment train, test, detect runs/
* Update ci-testing.yml
* inference/images to data/images
* move images
* runs/exp to runs/train/exp
* update 'results saved to %s' str
2020-11-08 19:39:05 +01:00
187f7c2ed1
Change optimizer parameters group method ( #1239 )
...
* Change optimizer parameters group method
* Add torch nn
* Change isinstance method(torch.Tensor to nn.Parameter)
* parameter freeze fix, PEP8 reformat
* freeze bug fix
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-11-02 00:08:36 +01:00
96fcde40b8
W&B feature improvements ( #1258 )
...
* W&B feature improvements
This PR add:
* Class to id labels. Now, the caption of bounding boxes will display the class name and the class confidence score.
* The project name is set to "Yolov5" and the run name will be set to opt.logdir
* cleanup
* remove parenthesis on caption
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-11-01 20:54:29 +01:00
ca290dca24
Weights & Biases (W&B) Feature Addition ( #1235 )
...
* Add wandb metric logging and bounding box debugging
* Improve formatting, readability
* Remove mutliple path for init, improve formatting
* Add wandb params
* Remove typecasting in bbox coordinates and reformat
* Cleanup
* add wandb to requirements.txt
* minor updates to test.py
* general reorg
* reduce --log-imgs to 10
* clean wandb import
* reverse wandb import assert
* add except AssertionError to try import
* move wandb init to all global ranks
* replace print() with logger.info()
* replace print() with logger.info()
* move wandb.init() bug fix
* project PosixPath to basename bug fix
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-10-31 20:16:35 +01:00
453acdec67
Update tensorboard logging
2020-10-26 01:08:33 +01:00
c67e72200e
fix compatibility for hyper config ( #1146 )
...
* fix/hyper
* Hyp giou check to train.py
* restore general.py
* train.py overwrite fix
* restore general.py and pep8 update
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-10-15 15:05:58 +02:00
4d3680c81d
Minor import and spelling updates ( #1133 )
2020-10-13 17:24:27 +02:00
00917a6225
update expt name comment and folder parsing for training ( #978 )
...
* comment
* fix parsing
* fix evolve
* folder
* tqdm
* Update train.py
* Update train.py
* reinstate anchors into meta dict
anchor evolution is working correctly now
* reinstate logger
prefer the single line readout for concise logging, which helps simplify notebook and tutorials etc.
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-10-13 14:10:21 +02:00
0ada058f63
Generalized regression criterion renaming ( #1120 )
2020-10-11 17:25:17 +02:00
5fac5ad165
Precision-Recall Curve Feature Addition ( #1107 )
...
* initial commit
* Update general.py
Indent update
* Update general.py
refactor duplicate code
* 200 dpi
2020-10-09 14:50:59 +02:00
66676eb039
init_torch_seeds >> init_seeds bug fix
2020-10-06 15:00:47 +02:00
f1c63e2784
add mosaic and warmup to hyperparameters ( #931 )
2020-09-13 14:03:54 -07:00
a62a45b2dd
prevent testloader caching on --notest
2020-09-11 16:59:13 -07:00
c8e51812a5
hyp evolution force-autoanchor fix
2020-09-04 13:13:10 -07:00
c687d5c129
reorganize train initialization steps
2020-09-04 12:25:53 -07:00
44cdcc7e0b
hyp['anchors'] evolution update
2020-09-03 12:54:22 -07:00
d8274d0434
Fix results_file not renaming ( #903 )
2020-09-03 00:47:50 -07:00
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
2020-09-02 15:08:43 -07:00
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>
2020-09-02 09:05:31 -07:00
f06e2d518c
opt.image_weights bug fix ( #885 )
2020-08-31 11:05:37 -07:00
69ff781ca5
opt.img_weights bug fix ( #885 )
2020-08-31 10:33:07 -07:00
08e97a2f88
Update hyperparameters to add lrf, anchors
2020-08-28 14:58:43 -07:00
a21bd0687c
Update train.py forward simplification
2020-08-25 13:48:03 -07:00
09402a2174
torch.from_tensor() bug fix
2020-08-25 03:14:17 -07:00
83dc540b1d
remove ema.ema hasattr(ema, 'module') check
2020-08-22 15:18:39 -07:00
4447f4b937
--resume to same runs/exp directory ( #765 )
...
* initial commit
* add weight backup dir on resume
2020-08-20 18:24:33 -07:00
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>
2020-08-18 09:52:21 -07:00
ebafd1ead5
single command --resume ( #756 )
...
* single command --resume
* else check files, remove TODO
* argparse.Namespace()
* tensorboard lr
* bug fix in get_latest_run()
2020-08-17 16:28:43 -07:00
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
2020-08-13 14:25:05 -07:00
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>
2020-08-12 14:18:19 -07:00
a925f283a7
max workers for dataloader ( #722 )
2020-08-12 13:57:36 -07:00
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>
2020-08-11 11:18:45 -07:00
e71fd0ec0b
Model freeze capability ( #679 )
2020-08-10 22:49:43 -07:00
8e5c66579b
update train.py remove save_json final_epoch
2020-08-09 21:24:40 -07:00
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
2020-08-09 20:52:57 -07:00
3d8ed0a76b
Fix missing model.stride in DP and DDP mode ( #683 )
2020-08-09 11:01:36 -07:00
a0ac5adb7b
Single-source training update ( #680 )
2020-08-09 02:27:35 -07:00
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
2020-08-09 02:12:44 -07:00
d7cfbc47ab
Fix unrecognized local rank argument ( #676 )
2020-08-08 16:40:10 -07:00
93684531c6
train.py --logdir argparser addition ( #660 )
...
* train.py --logdir argparser addition
* train.py --logdir argparser addition
2020-08-06 22:26:38 -07:00
886b9841c8
Add Multi-Node support for DDP Training ( #504 )
...
* Add support for multi-node DDP
* Remove local_rank confusion
* Fix spacing
2020-08-06 11:15:24 -07:00
728efa6576
Fix missing imports ( #627 )
...
* Fix missing imports
* Update detect.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-08-04 12:22:15 -07:00
eb99dff9ef
import random bug fix ( #614 )
2020-08-03 10:52:59 -07:00
d5b6416c87
Explicit Imports ( #498 )
...
* expand imports
* optimize
* miss
* fix
2020-08-02 15:47:36 -07:00
f1096b2cf7
hyperparameter evolution update ( #566 )
2020-08-02 10:32:04 -07:00
c1a2a7a411
hyperparameter evolution bug fix ( #566 )
2020-08-01 23:00:10 -07:00
8074745908
hyperparameter evolution bug fix ( #566 )
2020-08-01 19:24:14 -07:00
e32abb5fb9
hyperparameter evolution bug fix ( #566 )
2020-08-01 19:15:48 -07:00
8056fe2db8
hyperparameter evolution bug fix ( #566 )
2020-08-01 15:07:40 -07:00
127cbeb3f5
hyperparameter expansion to flips, perspective, mixup
2020-08-01 13:47:54 -07:00
bcd452c482
replace random_affine() with random_perspective()
...
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-07-31 15:53:52 -07:00
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
2020-07-31 10:52:45 -07:00
4e2b9ecc7e
LR --resume repeat bug fix ( #565 )
2020-07-30 10:48:20 -07:00
a209a32019
Fix bug #541 #542 ( #545 )
...
* fix #541 #542
* Update train.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-07-28 18:31:01 -07:00
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>
2020-07-25 10:24:39 -07:00
9da56b62dd
v2.0 Release ( #491 )
...
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-07-23 15:34:23 -07:00
5e970d45c4
Update train.py ( #462 )
2020-07-22 12:32:03 -07:00
3edc38f603
update train.py gsutil bucket fix ( #463 )
2020-07-21 23:25:33 -07:00
776555771f
update train.py gsutil bucket fix ( #463 )
2020-07-21 23:21:36 -07:00
b569ed6d6b
pretrained model loading bug fix ( #450 )
...
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-07-19 22:12:55 -07:00
4102fcc9a7
[WIP] Feature/ddp fixed ( #401 )
...
* Squashed commit of the following:
commit d738487089e41c22b3b1cd73aa7c1c40320a6ebf
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 e742dd9619d29306c7541821238d3d7cddcdc508
Author: yizhi.chen <chenyzsjtu@outlook.com>
Date: Tue Jul 14 15:38:48 2020 +0800
Make SyncBN a choice
commit e90d4004387e6103fecad745f8cbc2edc918e906
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 cd9036017e7f8bd519a8b62adab0f47ea67f4962
Author: NanoCode012 <kevinvong@rocketmail.com>
Date: Tue Jul 14 13:39:29 2020 +0700
Update train.py
Remove redundant `opt.` prefix.
commit 5bf8bebe8873afb18b762fe1f409aca116fac073
Merge: c9558a9 a1c8406https://github.com/ultralytics/yolov5 into feature/DDP_fixed
commit c9558a9b51547febb03d9c1ca42e2ef0fc15bb31
Author: yizhi.chen <chenyzsjtu@outlook.com>
Date: Tue Jul 14 13:51:34 2020 +0800
Add device allocation for loss compute
commit 4f08c692fb5e943a89e0ee354ef6c80a50eeb28d
Author: yizhi.chen <chenyzsjtu@outlook.com>
Date: Thu Jul 9 11:16:27 2020 +0800
Revert drop_last
commit 1dabe33a5a223b758cc761fc8741c6224205a34b
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 a1ce9b1e96b71d7fcb9d3e8143013eb8cebe5e27
Author: yizhi.chen <chenyzsjtu@outlook.com>
Date: Thu Jul 9 11:15:21 2020 +0800
fix lr warning
commit 4b8450b46db76e5e58cd95df965d4736077cfb0e
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 02c63ef81cf98b28b10344fe2cce08a03b143941
Author: NanoCode012 <kevinvong@rocketmail.com>
Date: Wed Jul 8 10:08:30 2020 +0700
Add drop_last for multi gpu
commit b9a50aed48ab1536f94d49269977e2accd67748f
Merge: ec2dc6c 121d90bhttps://github.com/ultralytics/yolov5 into feature/DDP_fixed
commit ec2dc6cc56de43ddff939e14c450672d0fbf9b3d
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 d0326e398dfeeeac611ccc64198d4fe91b7aa969
Author: yizhi.chen <chenyzsjtu@outlook.com>
Date: Tue Jul 7 19:31:24 2020 +0800
Add SyncBN
commit 82a6182b3ad0689a4432b631b438004e5acb3b74
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 050b2a5a79a89c9405854d439a1f70f892139b1c
Author: NanoCode012 <kevinvong@rocketmail.com>
Date: Tue Jul 7 12:38:14 2020 +0700
Add cleanup for process_group
commit 2aa330139f3cc1237aeb3132245ed7e5d6da1683
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 77c8e27e603bea9a69e7647587ca8d509dc1990d
Author: NanoCode012 <kevinvong@rocketmail.com>
Date: Tue Jul 7 01:54:39 2020 +0700
Convert BatchNorm to SyncBatchNorm
commit 96fa40a3a925e4ffd815fe329e1b5181ec92adc8
Author: yizhi.chen <chenyzsjtu@outlook.com>
Date: Mon Jul 6 21:53:56 2020 +0800
Fix the datset inconsistency problem
commit 16e7c269d062c8d16c4d4ff70cc80fd87935dc95
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 e83805563065ffd2e38f85abe008fc662cc17909
Merge: 625bb49 3bdea3fhttps://github.com/ultralytics/yolov5 into feature/DDP_fixed
commit 625bb49f4e52d781143fea0af36d14e5be8b040c
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 37acbdchttps://github.com/ultralytics/yolov4 into feature/DDP_fixed
commit 37acbdc0b6b8c2da4a0dhttps://github.com/MagicFrogSJTU/yolov5 into feature/DDP_fixed
commit cd55b445c4dcd8003ff4b0b46b64adf7c16e5ce7
Author: yizhi.chen <chenyzsjtu@outlook.com>
Date: Wed Jul 15 16:42:33 2020 +0800
fix the DDP performance deterioration bug.
commit 0f3b8bb1fae5885474ba861bbbd1924fb622ee93
Author: Glenn Jocher <glenn.jocher@ultralytics.com>
Date: Wed Jul 15 00:28:53 2020 -0700
Delete README.md
commit f5921ba1e35475f24b062456a890238cb7a3cf94
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 bd3fdbbf1b08ef87931eef49fa8340621caa7e87
Author: Glenn Jocher <glenn.jocher@ultralytics.com>
Date: Tue Jul 14 18:38:20 2020 -0700
Update README.md
commit c1a97a7767ccb2aa9afc7a5e72fd159e7c62ec02
Merge: 2bf86b8 f796708https://github.com/MagicFrogSJTU/yolov5 into feature/DDP_fixed
commit 5a19011949398d06e744d8d5521ab4e6dfa06ab7
Author: yizhi.chen <chenyzsjtu@outlook.com>
Date: Tue Jul 14 22:19:15 2020 +0800
Add assertion for <=2 gpus DDP
commit c8357ad5b15a0e6aeef4d7fe67ca9637f7322a4d
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 787582f97251834f955ef05a77072b8c673a8397
Author: NanoCode012 <kevinvong@rocketmail.com>
Date: Tue Jul 14 20:38:58 2020 +0700
Fixed issue with single gpu not having world_size
commit 63648925288d63a21174a4dd28f92dbfebfeb75a
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 69364d6050e048d0d8834e0f30ce84da3f6a13f3
Author: NanoCode012 <kevinvong@rocketmail.com>
Date: Tue Jul 14 17:36:48 2020 +0700
Changed number of workers check
commit d738487089e41c22b3b1cd73aa7c1c40320a6ebf
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 e742dd9619d29306c7541821238d3d7cddcdc508
Author: yizhi.chen <chenyzsjtu@outlook.com>
Date: Tue Jul 14 15:38:48 2020 +0800
Make SyncBN a choice
commit e90d4004387e6103fecad745f8cbc2edc918e906
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 cd9036017e7f8bd519a8b62adab0f47ea67f4962
Author: NanoCode012 <kevinvong@rocketmail.com>
Date: Tue Jul 14 13:39:29 2020 +0700
Update train.py
Remove redundant `opt.` prefix.
commit 5bf8bebe8873afb18b762fe1f409aca116fac073
Merge: c9558a9 a1c8406https://github.com/ultralytics/yolov5 into feature/DDP_fixed
commit c9558a9b51547febb03d9c1ca42e2ef0fc15bb31
Author: yizhi.chen <chenyzsjtu@outlook.com>
Date: Tue Jul 14 13:51:34 2020 +0800
Add device allocation for loss compute
commit 4f08c692fb5e943a89e0ee354ef6c80a50eeb28d
Author: yizhi.chen <chenyzsjtu@outlook.com>
Date: Thu Jul 9 11:16:27 2020 +0800
Revert drop_last
commit 1dabe33a5a223b758cc761fc8741c6224205a34b
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 a1ce9b1e96b71d7fcb9d3e8143013eb8cebe5e27
Author: yizhi.chen <chenyzsjtu@outlook.com>
Date: Thu Jul 9 11:15:21 2020 +0800
fix lr warning
commit 4b8450b46db76e5e58cd95df965d4736077cfb0e
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 02c63ef81cf98b28b10344fe2cce08a03b143941
Author: NanoCode012 <kevinvong@rocketmail.com>
Date: Wed Jul 8 10:08:30 2020 +0700
Add drop_last for multi gpu
commit b9a50aed48ab1536f94d49269977e2accd67748f
Merge: ec2dc6c 121d90bhttps://github.com/ultralytics/yolov5 into feature/DDP_fixed
commit ec2dc6cc56de43ddff939e14c450672d0fbf9b3d
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 d0326e398dfeeeac611ccc64198d4fe91b7aa969
Author: yizhi.chen <chenyzsjtu@outlook.com>
Date: Tue Jul 7 19:31:24 2020 +0800
Add SyncBN
commit 82a6182b3ad0689a4432b631b438004e5acb3b74
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 050b2a5a79a89c9405854d439a1f70f892139b1c
Author: NanoCode012 <kevinvong@rocketmail.com>
Date: Tue Jul 7 12:38:14 2020 +0700
Add cleanup for process_group
commit 2aa330139f3cc1237aeb3132245ed7e5d6da1683
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 77c8e27e603bea9a69e7647587ca8d509dc1990d
Author: NanoCode012 <kevinvong@rocketmail.com>
Date: Tue Jul 7 01:54:39 2020 +0700
Convert BatchNorm to SyncBatchNorm
commit 96fa40a3a925e4ffd815fe329e1b5181ec92adc8
Author: yizhi.chen <chenyzsjtu@outlook.com>
Date: Mon Jul 6 21:53:56 2020 +0800
Fix the datset inconsistency problem
commit 16e7c269d062c8d16c4d4ff70cc80fd87935dc95
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 e83805563065ffd2e38f85abe008fc662cc17909
Merge: 625bb49 3bdea3fhttps://github.com/ultralytics/yolov5 into feature/DDP_fixed
commit 625bb49f4e52d781143fea0af36d14e5be8b040c
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>
2020-07-19 12:33:30 -07:00
07493a715c
update train.py class count assertion #424
...
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-07-19 01:57:42 -07:00
912c06a67c
update train.py class count assertion #424
2020-07-19 01:51:41 -07:00
65857adf52
update train.py ckpt loading
2020-07-18 14:34:12 -07:00
03489aaafb
comment tb_writer.add_hparams(hyp, {})
2020-07-15 10:38:32 -07:00
1e94bcf3d2
Merge pull request #384 from jancio/master
...
Log hyperparameters in tensorboard
2020-07-14 12:32:27 -07:00
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.
2020-07-14 12:32:08 -07:00
38acc5f3c5
Fix img_size naming in hyperparameters logging
2020-07-14 08:48:46 +02:00
a1c8406af3
EMA and non_blocking=True
2020-07-13 20:19:10 -07:00
140d84cca1
comment updates
2020-07-13 12:17:52 -07:00
e558963244
Log hyperparameters in tensorboard
...
Log both hyperparameters and command line options in tensorboard.
2020-07-13 12:55:43 +02:00
01a73ec08e
multi-gpu ckpt filesize bug fix #253
2020-07-11 12:39:27 -07:00
a586751904
multi-gpu ckpt filesize bug fix #253
2020-07-11 12:35:21 -07:00
5de4e25d68
update tensorboard metric
2020-07-11 11:39:02 -07:00
98fc483abc
train.py results.txt to bucket bug fix
2020-07-11 09:31:53 -07:00
1c13e67b33
evolution bug fix #346
2020-07-09 22:08:42 -07:00
e16e9e43e1
new nc=len(names) check
2020-07-09 17:10:43 -07:00
cb527d3af9
new nc=len(names) check
2020-07-09 17:03:12 -07:00
603ea0bfdc
update log_dir to runs/exp #107
2020-07-09 15:58:07 -07:00
72d5b58b9a
disable LR plot to suppress warning message
2020-07-09 15:16:57 -07:00
24c5a941f0
--resume EMA fix #292
2020-07-09 15:09:06 -07:00
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
2020-07-09 16:18:55 -05:00
bf6f41567a
hyperparameter printout update
2020-07-08 17:21:00 -07:00
dc5e18390a
Merge branch 'master' into advanced_logging
2020-07-08 17:01:19 -07:00
6b134d93c5
Update train.py
2020-07-08 16:58:13 -07:00
16f6834486
update train.py and experimental.py
2020-07-08 14:23:34 -07:00
52bac22f09
Add in --resume functionality with option to specify path or to get most recent run
2020-07-07 10:42:28 -05:00
f517ba81c7
Merge branch 'master' into advanced_logging
2020-07-06 16:52:11 -05:00
956511dafd
fix LR bug
2020-07-05 15:08:24 +08:00
bb3c346916
model.yaml nc inherited from dataset.yaml
2020-07-04 17:51:54 -07:00
df224a0d8f
EMA bug fix #279
2020-07-03 11:56:14 -07:00
3bdea3f697
strip_optimizer() bug fix #253
2020-07-02 21:24:26 -07:00
e02a189a3a
Merge pull request #245 from yxNONG/patch-2
...
Unify the check point of single and multi GPU
2020-07-02 12:05:46 -07:00
597ed4ce63
Update train.py
2020-07-02 12:00:55 -07:00
13f69777a6
typo fix
2020-07-02 09:26:03 -07:00
1aa2b67933
Update train.py
2020-07-02 13:51:52 +08:00
86784cfdbf
--resume bug fix #252
2020-06-30 21:43:53 -07:00
ad4c22cbfe
--resume bug fix #187
2020-06-30 16:16:29 -07:00
3b16c865f0
assert --epochs
2020-06-30 14:08:08 -07:00
cdb9bde181
Unify the check point of single and multi GPU
...
save the model.hyp etc to checkpoint when use multi GPU training
2020-06-30 19:06:28 +08:00
b203c9b7ff
update train.py incompatible model message fix #222
2020-06-29 12:45:25 -07:00
37e13f8846
update mosaic border
2020-06-27 13:50:15 -07:00
e18e6811dc
Merge branch 'master' into advanced_logging
2020-06-27 10:13:03 -05:00
22fb2b0c25
refactor dataloader
2020-06-26 18:56:13 -07:00
256a3e89d2
small dataset bug fix #140
2020-06-25 17:52:56 -07:00
b50fdf16af
model.names multi-GPU bug fix #94
2020-06-24 22:22:13 -07:00
de191655e4
Fix yaml saving (don't sort keys), reorder --opt keys, bug fix hyp dict accessor
2020-06-24 17:21:54 -05:00
2d396bea00
Fix bug in --help from percent sign in help string
2020-06-24 16:57:12 -05:00
b8557f87e3
add stride to datasets.py
2020-06-24 13:02:27 -07:00
611aacf1bf
Turn opt into dictionary before sending it to yaml
2020-06-24 10:49:08 -05:00
bc4ef4861b
Default optimizer SGD
2020-06-24 10:07:43 -05:00
7abf202cad
Mode all optimizer settings to 'hyp.yaml', integrate proper momentum with Adam optimizer
2020-06-24 10:03:21 -05:00
7edbf6570e
Fix help message for cfg files
2020-06-24 09:45:57 -05:00
d64ad0fbf3
Remove --resume functionality and related checks/logic.
2020-06-24 09:17:27 -05:00
6c1b87a42e
update google_utils import
2020-06-22 23:00:23 -07:00
1f1917ef56
remove fast, add merge
2020-06-21 13:37:11 -07:00
e572bb0803
Add plot_results save location to log_dir
2020-06-21 09:36:28 -05:00
899f1d4bde
Fix DDP bug in single process multiple device use cases
2020-06-20 13:00:03 +08:00
cdf1eac9f7
Merge pull request #107 from Lornatang/fix-reference-bugs
...
fix refrence bug
2020-06-19 14:51:41 -07:00
cce95e744d
backbone as FP16, save default to FP32
2020-06-18 00:13:18 -07:00
d9b64c27c2
save ckpt in FP16 #119
2020-06-17 22:34:13 -07:00
9fdb0fbacf
AutoAnchor bug fix # 117
2020-06-17 19:51:15 -07:00
c8152c81a6
Syntax fixes
2020-06-17 16:32:13 -05:00
9b7386f603
Add save_dir arg to test.test, use arg as location for saving batch jpgs
2020-06-17 16:08:46 -05:00
945307beba
Add save_dir to plot_lr_scheduler and plot_labels
...
Set save_dir = log_dir in train.py
2020-06-17 16:03:18 -05:00
3b2b330872
Move results.txt from weights/ to log_dir
2020-06-17 15:55:45 -05:00
ade023cff2
Fix hyp file read in and dict update.
...
Add example of hyp yaml
2020-06-17 10:59:20 -05:00
2368603484
fix refrence bug
...
In torch==1.5, the import of the API has changed. Although it does not interrupt the operation of the program, it seems to me to be an implicit error and may throw an exception in later versions.
2020-06-17 09:56:26 +08:00
8db51c7002
tb_writer bug fix
2020-06-16 16:05:28 -07:00
5f2eeba233
remove old print statements
2020-06-16 17:09:39 -05:00
afe1df385b
dist.destroy_process_group() bug fix
2020-06-16 15:08:14 -07:00
333f678b37
add update default hyp dict with provided yaml
2020-06-16 16:36:20 -05:00
a448c3bcd7
add logic for resuming and getting hyp for resume run
2020-06-16 16:30:12 -05:00
25e51bcec7
add util function to get most recent last.pt file
...
added logic in train.py __main__ to handle resuming from a run
2020-06-16 15:50:27 -05:00
490f1e7b9c
add save_dir arg to plot_lr_scheduler, default to current dir.
...
Uncomment plot_lr_scheduler in train() and pass log_dir as save location
2020-06-16 15:13:03 -05:00
4418809cf5
change weights dir (wdir) to be unique to each run, under log_dir
2020-06-16 15:09:51 -05:00
d9f446cd81
add save yaml of opt and hyp to tensorboard log_dir in train()
2020-06-16 15:06:13 -05:00
a85e6d0fc0
add parser arg for hyp yaml file
2020-06-16 14:53:32 -05:00
5a50491fa1
check_anchors bug fix
2020-06-16 10:36:35 -07:00
05b8ee5ca4
check_anchors() bug fix #102
2020-06-16 10:34:16 -07:00
ec81c7b5f2
check_anchors() bug fix #90
2020-06-16 10:14:04 -07:00
8b26e89006
AutoAnchor bug fix #72
2020-06-16 00:53:34 -07:00
bdd9fee841
update fast mode
2020-06-16 00:29:54 -07:00
1c0b6236e3
update fast mode
2020-06-16 00:11:29 -07:00
915b1481fc
default check_git_status() to True
2020-06-15 16:18:46 -07:00
14523bb030
FP16 to FP32 ckpt load
2020-06-15 13:18:39 -07:00
c5966abba8
glob search bug fix #77
2020-06-15 12:08:57 -07:00
31f3310029
assert best possible recall > 0.9 before training
2020-06-13 15:05:41 -07:00
c3d4d321d3
Ensures weights/ dir exists
...
Allows train.py to be run outside of yolov5/ directory.
2020-06-13 14:44:23 +02:00
099e6f5ebd
--img-size stride-multiple verification
2020-06-12 22:10:46 -07:00
22d6088205
speed-reproducibility fix #17
2020-06-05 13:07:09 -07:00
55ca5c74d2
multi-scale fix #16
2020-06-05 12:57:16 -07:00
7c2832cd49
assert equal model and dataset classes
2020-06-04 17:21:22 -07:00
11121e39ed
updates
2020-06-04 16:52:07 -07:00
eb97b2e413
NMS fast mode
2020-06-03 13:02:59 -07:00
ce36905358
updates
2020-05-30 00:12:45 -07:00
1e84a23f38
initial commit
2020-05-29 17:04:54 -07:00
Glenn Jocher
asim266
Khiem Doan
Junghoon Kim
Ayush Chaurasia
Jirka Borovec
NanoCode012
Naman Gupta
Marc
lorenzomammana
Liu Changyu
Laughing
AlexWang1900
yzchen
Janko Ondras
Alex Stoken
yxNONG
Lauritzen Kasper Primdal