Glenn Jocher
ed85038c38
Precision-Recall Curve feature update ( #1206 )
...
* Precision-Recall Curve feature update
* sentinel value update
2020-10-25 12:55:52 +01:00
Glenn Jocher
481d46cffb
Improved corruption handling during scan and cache ( #999 )
2020-10-24 15:09:19 +02:00
Glenn Jocher
d61930e017
Improved corruption handling during scan and cache ( #999 )
2020-10-24 14:50:50 +02:00
Shiwei Song
9291daa6f7
fix padding for rectangular inference ( #1165 )
...
Co-authored-by: swsong <swsong@stratosphere.mobi>
2020-10-19 12:22:22 +02:00
Glenn Jocher
3b57cb5641
Simplified inference ( #1153 )
2020-10-15 20:10:08 +02:00
Jirka Borovec
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
Glenn Jocher
4d3680c81d
Minor import and spelling updates ( #1133 )
2020-10-13 17:24:27 +02:00
Jirka Borovec
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
Glenn Jocher
0ada058f63
Generalized regression criterion renaming ( #1120 )
2020-10-11 17:25:17 +02:00
Glenn Jocher
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
Glenn Jocher
124f0e8212
torchvision nms bug fix
2020-10-06 15:09:24 +02:00
Glenn Jocher
883924d9dc
classifier, export, torch seed updates
2020-10-06 14:54:02 +02:00
Jiacong Fang
c5d2331897
Fix increment_dir to use run_xxx for logdir ( #1058 )
...
* Fix increment_dir to use run_xxx for logdir
Rerunning train.py with logdir in the form of `run_xxx` causes index slicing in
```
n = max([int(x[len(dir):x.find('_') if '_' in Path(x).name else None]) for x in d]) + 1 # increment
```
to underflow.
* Replace find with rfind
2020-10-05 15:46:32 +02:00
haoyuefan
7220cee1d1
mosaic4 bottom left image fix ( #1021 )
...
fix a bug in load_mosaic
2020-09-23 09:51:33 -07:00
Guilhen
702c4fa53e
adding the configuration to deploy yolov5 in in app engine ( #964 )
...
* add the configuration to deploy yolov5 in a docker container in app engine on google cloud
* remove the duplicated requirements, place the google app engine files in utils
* remove the unused requirements
Co-authored-by: guilhembau <guilhem@6dbytes.com>
2020-09-22 11:48:44 -07:00
Glenn Jocher
89655a84f2
.fuse() gradient introduction bug fix
2020-09-20 11:57:19 -07:00
Glenn Jocher
5a9c5c1d3b
add mosaic and warmup to hyperparameters ( #931 )
2020-09-13 14:08:06 -07:00
Glenn Jocher
f1c63e2784
add mosaic and warmup to hyperparameters ( #931 )
2020-09-13 14:03:54 -07:00
Glenn Jocher
806e75f2b1
self.label_files bug fix ( #958 )
2020-09-13 11:38:23 -07:00
Glenn Jocher
c54e39464c
check_file() assert unique
2020-09-11 14:33:06 -07:00
Glenn Jocher
720645d96a
LoadImagesAndLabels() /images/ to /labels/ fix ( #928 )
2020-09-10 12:29:05 -07:00
Glenn Jocher
d49c52eee3
_RepeatSampler outside of InfiniteDataLoader
2020-09-10 12:27:35 -07:00
Glenn Jocher
9c0efdde9f
glob.glob(recursive=True) search ( #917 )
2020-09-06 22:52:28 -07:00
Glenn Jocher
bc1fd13a7a
gsutil cp hyp evolution bug fix ( #876 )
2020-09-03 20:29:08 -07:00
Glenn Jocher
44cdcc7e0b
hyp['anchors'] evolution update
2020-09-03 12:54:22 -07:00
Glenn Jocher
ffe9eb4238
remove if platform.system() == 'Darwin' checks
2020-09-03 11:41:33 -07:00
tkianai
c5969f79f5
add support for DWConv fuse operation ( #898 )
...
* the value should be a list to unpacking
* filter the None labels
* update readme to remove apex dependency
* add support for DWConv fuse operation
2020-09-01 22:18:42 -07:00
Glenn Jocher
d3f9bf2bb7
Update datasets.py
2020-09-01 17:02:47 -07:00
NanoCode012
1e15aad6f9
Add InfiniteDataLoader class ( #876 )
...
* Add InfiniteDataLoader
Only initializes at first epoch. Saves time.
* Moved class to a better location
2020-08-31 11:01:25 -07:00
Glenn Jocher
987c226849
seaborn plotting correlogram addition
2020-08-29 15:13:58 -07:00
rafale77
9776e70988
torch.ops.torchvision.nms ( #860 )
...
Don't load the entire torchvision library just for nms when the function is already in the torch library.
2020-08-27 11:13:41 -07:00
Glenn Jocher
31d6c389f2
Update general.py plot_evolution()
2020-08-25 23:08:14 -07:00
Willie Maddox
455f7b8f76
Update general.py ( #823 )
...
Fixes #822
`init_seeds` from `torch_utils` import is being overwritten by function `init_seeds` in `general.py`
2020-08-25 13:01:17 -07:00
Glenn Jocher
5a7d79fbe6
Update general.py bbox_iou() with eps improvements ( #736 )
...
eps reduced to 1e-9 for additional precaution.
2020-08-25 12:56:39 -07:00
Glenn Jocher
82ed33a052
generalize webcam detection with opt.source.isnumeric() (yolov3 #1462 )
2020-08-25 11:07:38 -07:00
Glenn Jocher
4d7f222f73
Update export.py with v3.0 Hardswish() support
2020-08-24 21:47:49 -07:00
Glenn Jocher
8666bc507e
Create evolve.sh for infinite hyp evolution
2020-08-24 20:27:28 -07:00
Glenn Jocher
71209a6099
exportable Hardswish() implementation
2020-08-22 16:59:31 -07:00
Glenn Jocher
f7e075fe93
gsutil cp yaml when evolving to GCP bucket
2020-08-22 15:47:39 -07:00
Glenn Jocher
9dbaa1bbbe
Update plot_results()
2020-08-22 15:32:05 -07:00
Glenn Jocher
ea5e97fb9b
FP16 NMS ( #814 )
2020-08-21 14:44:25 -07:00
Glenn Jocher
b42e8a531b
optimize imports
2020-08-20 21:17:40 -07:00
Glenn Jocher
5e0b90de8f
CIoU nan bug fix ( #736 )
2020-08-20 10:37:55 -07:00
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()
2020-08-17 16:28:43 -07:00
Francisco Ingham
26c3b11fdc
Update torch_utils.py ( #751 )
2020-08-16 13:58:59 -07:00
Glenn Jocher
f5da528d28
reformat code
2020-08-14 11:53:44 -07:00
Quan Lin
66744a0df1
Update utils/google_utils.py ( #733 )
...
To download weights from v3.0 instead of v2.0
2020-08-13 18:44:14 -07:00
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
2020-08-13 14:25:05 -07:00
Hatovix
56c2c344ff
Fix list paths ( #721 )
...
* Add list paths on check_dataset
* missing raise statement
* Update general.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-08-12 18:53:38 -07:00
Marc
a925f283a7
max workers for dataloader ( #722 )
2020-08-12 13:57:36 -07:00
Glenn Jocher
d2da523053
Merge remote-tracking branch 'origin/master'
2020-08-11 20:11:58 -07:00
Glenn Jocher
9f482cbcb8
utils.general comment updates/bug fixes
2020-08-11 20:11:44 -07:00
Marc
1f92422e20
Github release assets model autodownload ( #711 )
...
* assets autodownload
* Update google_utils.py
* Update google_utils.py
* Update google_utils.py
* Update google_utils.py
* Update google_utils.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-08-11 17:17:24 -07:00
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>
2020-08-11 11:18:45 -07:00
tkianai
542833c997
Filter the None labels ( #705 )
...
* the value should be a list to unpacking
* filter the None labels
2020-08-11 11:15:48 -07:00
tkianai
9ae868364a
the value should be a list to unpacking ( #688 )
2020-08-10 11:23:48 -07:00
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
2020-08-09 20:52:57 -07:00
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
2020-08-09 02:12:44 -07:00
Glenn Jocher
3fcd365ba3
Fix curl download on Windows ( #669 )
2020-08-07 12:13:55 -07:00
NanoCode012
fe5b3f8712
Fix curl download on Windows ( #669 )
...
* Update ci-testing.yml
* Fix windows download
* Fix cookie and curl download issue from gdrive
* Revert "Update ci-testing.yml"
This reverts commit 7389d2238d
.
* Update google_utils.py
PEP8
* Update google_utils.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-08-07 12:10:59 -07:00
Glenn Jocher
7eaf225d55
zero-target training bug fix ( #609 )
2020-08-05 13:35:31 -07:00
Glenn Jocher
f346da9f2b
update activations.py
2020-08-03 17:18:31 -07:00
Jirka Borovec
d5b6416c87
Explicit Imports ( #498 )
...
* expand imports
* optimize
* miss
* fix
2020-08-02 15:47:36 -07:00
Glenn Jocher
ec7a926163
AutoAnchor update to display anchors/target
2020-08-02 14:38:45 -07:00
Glenn Jocher
d989bc9260
remove NBSP
2020-08-02 14:23:05 -07:00
Glenn Jocher
023e37807c
hyperparameter evolution update ( #566 )
2020-08-02 13:18:03 -07:00
Glenn Jocher
64e6d199ba
hyperparameter evolution update ( #566 )
2020-08-02 13:17:26 -07:00
Glenn Jocher
305c6a028a
compute_loss() leaf variable update
2020-08-02 10:30:43 -07:00
Glenn Jocher
c1a2a7a411
hyperparameter evolution bug fix ( #566 )
2020-08-01 23:00:10 -07:00
Glenn Jocher
e32abb5fb9
hyperparameter evolution bug fix ( #566 )
2020-08-01 19:15:48 -07:00
Glenn Jocher
127cbeb3f5
hyperparameter expansion to flips, perspective, mixup
2020-08-01 13:47:54 -07:00
Glenn Jocher
23d2bde01f
leaf variable --single-cls training bug fix ( #593 )
2020-08-01 11:42:41 -07:00
Glenn Jocher
bcd452c482
replace random_affine() with random_perspective()
...
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-07-31 15:53:52 -07:00
Glenn Jocher
bb87276d80
update build_targets() ( #589 )
...
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-07-31 14:34:13 -07:00
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
2020-07-31 10:52:45 -07:00
Glenn Jocher
c8892672a7
Funnel ReLU (FReLU) @staticmethod bug fix ( #556 )
...
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-07-30 17:38:15 -07:00
Glenn Jocher
131782a2aa
Funnel ReLU (FReLU) ( #556 )
...
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-07-30 17:35:34 -07:00
AlexWang1900
4b074d9d9d
Funnel ReLU (FReLU) ( #556 )
...
* fix #541 #542
* Update train.py
* Add Frelu
* Update activations.py
PEP8 and format updates for commonality with models.common.Conv()
* Update activations.py
Update case
* Update activations.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-07-30 17:25:49 -07:00
YuriRibeiro
7d78b17a69
Fix utils.py nonzero() warning ( #551 )
2020-07-29 12:14:11 -07:00
AlexWang1900
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
Glenn Jocher
0032af2980
Update utils.py strip_optimizer() ( #509 )
2020-07-24 19:26:56 -07:00
Glenn Jocher
1d17b9af0f
update yolo.py TTA flexibility and extensibility ( #506 )
...
* update yolo.py TTA flexibility and extensibility
* Update scale_img()
2020-07-24 11:42:23 -07:00
Glenn Jocher
4b5f4806bc
Update datasets.py ( #494 )
2020-07-23 22:49:54 -07:00
Glenn Jocher
9da56b62dd
v2.0 Release ( #491 )
...
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-07-23 15:34:23 -07:00
Glenn Jocher
4ffd9779d3
plotting improvements ( #471 )
...
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-07-21 14:07:11 -07:00
pritul dave
1e95337f3a
Update datasets.py ( #454 )
2020-07-20 10:33:09 -07:00
Glenn Jocher
07a82f4d44
Update ci-testing.yml ( #445 )
...
* Update ci-testing.yml
* Update ci-testing.yml
* Update requirements.txt
* Update requirements.txt
* Update google_utils.py
* Update test.py
* Update ci-testing.yml
2020-07-19 15:44:11 -07:00
yzchen
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 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 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 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 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 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 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 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 65157e2fc97d371bc576e18b424e130eb3026917
Author: yizhi.chen <chenyzsjtu@outlook.com>
Date: Wed Jul 15 16:44:13 2020 +0800
Revert the README.md removal
commit 1c802bfa503623661d8617ca3f259835d27c5345
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 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 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 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 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 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 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 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 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 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
Glenn Jocher
aa08b2bd6f
test.py --task test updates
2020-07-15 18:25:34 -07:00
Glenn Jocher
98f4a5af87
runs/exp increment bug fix #344
2020-07-15 16:07:40 -07:00
Glenn Jocher
2377e5f6ee
FP16 EMA bug fix
2020-07-13 15:47:46 -07:00
Glenn Jocher
140d84cca1
comment updates
2020-07-13 12:17:52 -07:00
Glenn Jocher
8412d44dce
update datasets.py to add detect.py --source glob_command feature
2020-07-12 14:22:15 -07:00
Glenn Jocher
eae33303d6
update datasets.py LoadImages() path improvements and Mixup
2020-07-12 14:14:51 -07:00
Glenn Jocher
41ff83a98d
update torch_utils.py to FP16 EMA
2020-07-12 12:18:00 -07:00
Glenn Jocher
f7a6d6c8d4
remove https:// prefix from curl commands fix #355
2020-07-11 13:00:24 -07:00
Glenn Jocher
a586751904
multi-gpu ckpt filesize bug fix #253
2020-07-11 12:35:21 -07:00
Glenn Jocher
d6f6b33a49
update datasets.py for image size check during caching
2020-07-11 00:21:52 -07:00
Glenn Jocher
01a67a9742
Merge remote-tracking branch 'origin/master'
2020-07-10 20:36:26 -07:00
Glenn Jocher
d3e786ed93
google_utils.py bug fix #355
2020-07-10 20:36:10 -07:00
Glenn Jocher
41bb70b325
update create_pretrained()
2020-07-10 00:25:35 -07:00
Glenn Jocher
1531795f5e
avoid git status check in Docker bug fix #342
2020-07-10 00:11:50 -07:00
Glenn Jocher
1e9cf6a6e9
add file sizes to ckpt ops
2020-07-10 00:00:19 -07:00
Glenn Jocher
59beae98e8
add if isfile() to get_hash()
2020-07-09 20:57:24 -07:00
Glenn Jocher
6649770001
--rect test bug fix
2020-07-09 20:39:11 -07:00
Glenn Jocher
520f5de6f0
Label caching foundational re-write #306
2020-07-09 20:07:16 -07:00
Glenn Jocher
dd8e742ece
Merge pull request #334 from lorenzomammana/feature-multiple-datasets-training
...
Handle multiple datasets
2020-07-09 16:29:21 -07:00
Glenn Jocher
dd33d2ab77
Update datasets.py
2020-07-09 16:28:20 -07:00
Glenn Jocher
2110f5ee89
update log_dir to runs/exp #107
2020-07-09 16:03:10 -07:00
Glenn Jocher
603ea0bfdc
update log_dir to runs/exp #107
2020-07-09 15:58:07 -07:00
Glenn Jocher
24c5a941f0
--resume EMA fix #292
2020-07-09 15:09:06 -07:00
Glenn Jocher
13a09fa68a
Update datasets.py
2020-07-09 13:47:20 -07:00
Glenn Jocher
47bf1730fa
Update datasets.py
2020-07-09 13:45:55 -07:00
Glenn Jocher
f9bab6b127
Update datasets.py
2020-07-09 13:36:23 -07:00
lorenzomammana
54a9e4f876
Refactor code to reduce duplication
2020-07-09 19:39:28 +02:00
lorenzomammana
94342acbe1
Handle multiple datasets
2020-07-09 11:52:12 +02:00
Glenn Jocher
bf6f41567a
hyperparameter printout update
2020-07-08 17:21:00 -07:00
Glenn Jocher
dc5e18390a
Merge branch 'master' into advanced_logging
2020-07-08 17:01:19 -07:00
Glenn Jocher
cbe39a1dbb
Update utils.py
2020-07-08 16:14:32 -07:00
Glenn Jocher
c654d18f00
Update utils.py
2020-07-08 16:11:22 -07:00
Glenn Jocher
31b07b3550
Merge pull request #275 from wanghaoyang0106/master
...
[bug fix] potential problem if img fed to model is in rectangular shape
2020-07-08 00:07:54 -07:00
Glenn Jocher
e8cf24b6c8
Initial model ensemble capability #318
2020-07-07 15:40:50 -07:00
Alex Stoken
95f0a56df7
Bug fix to get_latest_run when recent run is named
2020-07-07 11:19:49 -05:00
Alex Stoken
f517ba81c7
Merge branch 'master' into advanced_logging
2020-07-06 16:52:11 -05:00
Glenn Jocher
121d90b3f2
update fuse_conv_and_bn()
2020-07-06 11:46:10 -07:00
Glenn Jocher
38f5c1ad1d
pruning and sparsity initial commit
2020-07-05 13:41:21 -07:00
NanoCode012
ccfa9373ae
Update to remove "module" attribute check
2020-07-04 23:12:57 +07:00
NanoCode012
f83521ab9a
Fix save error for multi-gpu
2020-07-04 16:50:33 +07:00
Glenn Jocher
ce0c58f678
update compute_loss()
2020-07-03 18:56:07 -07:00
Glenn Jocher
af41083d52
EMA FP16 fix #279
2020-07-03 16:57:08 -07:00
Glenn Jocher
f767023c56
offset and balance update
2020-07-03 14:07:00 -07:00
Glenn Jocher
df224a0d8f
EMA bug fix #279
2020-07-03 11:56:14 -07:00
wanghaoyang0106
b57f83d005
[bug fix] potential problem if img fed to model is in rectangular shape
2020-07-03 13:09:21 +08:00
Glenn Jocher
f02481c73a
Update torch_utils.py
2020-07-02 12:03:45 -07:00
Glenn Jocher
fc7c42723d
Update utils.py
2020-07-02 12:01:43 -07:00
yxNONG
53cdaf6bf5
Update utils.py
2020-07-02 13:48:19 +08:00
Glenn Jocher
9a9333d245
add replicate() to datasets.py
2020-06-29 17:10:33 -07:00
Glenn Jocher
37e13f8846
update mosaic border
2020-06-27 13:50:15 -07:00
Glenn Jocher
93a6765806
update mosaic border
2020-06-27 13:02:01 -07:00
Alex Stoken
e18e6811dc
Merge branch 'master' into advanced_logging
2020-06-27 10:13:03 -05:00
Glenn Jocher
77fb8ee082
refactor dataloader
2020-06-26 19:30:09 -07:00
Glenn Jocher
22fb2b0c25
refactor dataloader
2020-06-26 18:56:13 -07:00
Glenn Jocher
b8557f87e3
add stride to datasets.py
2020-06-24 13:02:27 -07:00
Glenn Jocher
3b062254a6
update utils.create_pretrained()
2020-06-24 12:53:43 -07:00
Glenn Jocher
6c1b87a42e
update google_utils import
2020-06-22 23:00:23 -07:00
Glenn Jocher
364fcfd7db
PANet update
2020-06-22 14:27:17 -07:00
Glenn Jocher
fc171e2678
check_anchor_order() update
2020-06-21 14:08:59 -07:00
Glenn Jocher
1f1917ef56
remove fast, add merge
2020-06-21 13:37:11 -07:00
Alex Stoken
e572bb0803
Add plot_results save location to log_dir
2020-06-21 09:36:28 -05:00
Glenn Jocher
024a42f4fd
datasets.py vid_formats updated
2020-06-20 09:53:37 -07:00
Glenn Jocher
5c2cd711df
vid_formats bug fix #146
2020-06-20 09:26:07 -07:00
Glenn Jocher
10145833c3
strip_optimizer() default to save FP16 model
2020-06-18 00:16:47 -07:00
Glenn Jocher
cce95e744d
backbone as FP16, save default to FP32
2020-06-18 00:13:18 -07:00
Glenn Jocher
9fdb0fbacf
AutoAnchor bug fix # 117
2020-06-17 19:51:15 -07:00
Alex Stoken
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
Alex Stoken
3263a204ea
Fix get_latest_run to search 'search_dir' recursivly
2020-06-17 10:34:37 -05:00
Alex Stoken
d34291733b
Fix get_latest_run() to search inside 'weights' subfolders
2020-06-17 10:26:55 -05:00
Glenn Jocher
a557b7d924
check_img_size() update
2020-06-16 17:48:01 -07:00
Glenn Jocher
034609414e
AutoAnchor fitness to screen
2020-06-16 17:08:45 -07:00
Glenn Jocher
ef75f7313d
AutoAnchor n, imgsz bug fix
2020-06-16 16:48:01 -07:00
Glenn Jocher
1dfc28527f
AutoAnchor BPR to 4 significant figures
2020-06-16 16:19:58 -07:00
Glenn Jocher
4052603e1f
AutoAnchor update - improvement check
2020-06-16 15:54:20 -07:00
Glenn Jocher
bafbc65ee3
AutoAnchor bug fix
2020-06-16 14:26:02 -07:00
Alex Stoken
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
Alex Stoken
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
Glenn Jocher
57a0ae3350
AutoAnchor implementation
2020-06-16 13:12:22 -07:00
Glenn Jocher
95c46f7245
Merge pull request #79 from Lornatang/delete-redundant-thrid-party-library
...
Delete redundant thrid party library
2020-06-16 11:52:36 -07:00
Glenn Jocher
ec81c7b5f2
check_anchors() bug fix #90
2020-06-16 10:14:04 -07:00
Glenn Jocher
8b26e89006
AutoAnchor bug fix #72
2020-06-16 00:53:34 -07:00
Glenn Jocher
8fa3724072
kmean_anchors() update
2020-06-16 00:40:21 -07:00
Glenn Jocher
1c0b6236e3
update fast mode
2020-06-16 00:11:29 -07:00
Lornatang
8b8b792802
There is no need to download extra packages, official bring it with you
...
I submitted it once in your yolov3 project, you seem to accept it? I'm not sure. I'll submit PR again.
2020-06-16 08:28:52 +08:00
Glenn Jocher
db2c3acd3a
updated testing settings, rebalanced towards FP16 latency
2020-06-15 16:55:57 -07:00
Glenn Jocher
bd3e389130
update google_utils.py
2020-06-15 14:39:04 -07:00
Glenn Jocher
c5966abba8
glob search bug fix #77
2020-06-15 12:08:57 -07:00
Lornatang
54795a4f0a
fix problem
2020-06-15 16:11:06 +08:00
Glenn Jocher
260b1729f0
FP16 inference update
2020-06-14 18:32:29 -07:00
Glenn Jocher
93bbf1b87a
best possible recall fix
2020-06-13 15:25:53 -07:00
Glenn Jocher
31f3310029
assert best possible recall > 0.9 before training
2020-06-13 15:05:41 -07:00
Glenn Jocher
099e6f5ebd
--img-size stride-multiple verification
2020-06-12 22:10:46 -07:00
Glenn Jocher
3a5c5328c5
ONNX, BCEBlurWithLogitsLoss, plot_study updates
2020-06-11 14:44:09 -07:00
Trevor Sullivan
ac93e9c811
Fix Google Drive URI for YOLOv5 weights
2020-06-10 14:26:10 -07:00
Glenn Jocher
c14368d768
new CSP model release
2020-06-09 14:31:04 -07:00
Glenn Jocher
ff02ae0869
module updates
2020-06-08 22:13:01 -07:00
Glenn Jocher
1f698af6f1
create_backbone with SourceChangeWarning update
2020-06-07 15:45:05 -07:00
Glenn Jocher
8fe299f179
model fuse
2020-06-07 14:10:30 -07:00
Glenn Jocher
b810b21299
augmented inference
2020-06-05 21:14:15 -07:00
Glenn Jocher
c12023f145
updates
2020-06-05 20:50:43 -07:00
Glenn Jocher
66d73e4cf3
NMS updates
2020-06-05 18:44:39 -07:00
Glenn Jocher
948bcdd219
--classes bug fix #17
2020-06-05 13:29:26 -07:00
Glenn Jocher
22d6088205
speed-reproducibility fix #17
2020-06-05 13:07:09 -07:00
Glenn Jocher
0362f103ef
updates
2020-06-04 10:19:06 -07:00
Glenn Jocher
2a0aff685a
dataset padding mode
2020-06-03 13:55:33 -07:00
Glenn Jocher
eb97b2e413
NMS fast mode
2020-06-03 13:02:59 -07:00
Glenn Jocher
ee8988b8a2
datasets.py self.batch_shapes fix
2020-06-01 18:11:18 -07:00
Glenn Jocher
f96e8f3edf
updates
2020-05-31 19:51:32 -07:00
Glenn Jocher
b10609fe6b
updates
2020-05-31 15:07:04 -07:00
Glenn Jocher
72eed215ff
updates
2020-05-31 09:25:42 -07:00
Glenn Jocher
5a79b5f65c
updates
2020-05-30 15:22:09 -07:00
Glenn Jocher
4f44aaf26b
updates
2020-05-30 15:18:59 -07:00
Glenn Jocher
1e84a23f38
initial commit
2020-05-29 17:04:54 -07:00