Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
326 commits
Select commit Hold shift + click to select a range
fef1913
`check_font()` on notebook init (#9200)
glenn-jocher Aug 29, 2022
bd5fd78
Comment `protobuf` in requirements.txt (#9207)
glenn-jocher Aug 29, 2022
da22e01
`check_font()` fstring update (#9208)
glenn-jocher Aug 29, 2022
3c64d89
AutoBatch protect from extreme batch sizes (#9209)
glenn-jocher Aug 29, 2022
91a81d4
Default AutoBatch 0.8 fraction (#9212)
glenn-jocher Aug 29, 2022
f37ac8d
Delete rebase.yml (#9202)
glenn-jocher Aug 30, 2022
5fb267f
Duplicate segment verification fix (#9225)
glenn-jocher Aug 30, 2022
6e7a7ae
New `LetterBox(size)` `CenterCrop(size)`, `ToTensor()` transforms (#9…
glenn-jocher Aug 30, 2022
4a37381
Add ClassificationModel TF export assert (#9226)
glenn-jocher Aug 30, 2022
5f1000a
Remove usage of `pathlib.Path.unlink(missing_ok=...)` (#9227)
ymerkli Aug 30, 2022
79e181a
Add support for *`.pfm` images (#9230)
spacewalk01 Aug 31, 2022
55b0096
Python check warning emoji (#9238)
glenn-jocher Aug 31, 2022
223c59d
Add `url_getsize()` function (#9247)
glenn-jocher Sep 1, 2022
c91d1db
Update dataloaders.py (#9250)
glenn-jocher Sep 1, 2022
2d082a0
Refactor Loggers : Move code outside train.py (#9241)
AyushExel Sep 1, 2022
ea98199
Update general.py (#9252)
glenn-jocher Sep 1, 2022
9da6d0f
Add LoadImages._cv2_rotate() (#9249)
glenn-jocher Sep 1, 2022
ffdb58b
Move `cudnn.benchmarks(True)` to LoadStreams (#9258)
glenn-jocher Sep 2, 2022
5d4787b
`cudnn.benchmark = True` on Seed 0 (#9259)
glenn-jocher Sep 2, 2022
15e82d2
Update `TryExcept(msg='...')`` (#9261)
glenn-jocher Sep 2, 2022
5cb9fe6
Make sure best.pt model file is preserved ClearML (#9265)
thepycoder Sep 3, 2022
63ecce6
DetectMultiBackend improvements (#9269)
glenn-jocher Sep 3, 2022
96c3c7f
Update DetectMultiBackend for tuple outputs (#9274)
glenn-jocher Sep 4, 2022
7aa263c
Update DetectMultiBackend for tuple outputs 2 (#9275)
glenn-jocher Sep 4, 2022
e45d335
Update benchmarks CI with `--hard-fail` min metric floor (#9276)
glenn-jocher Sep 4, 2022
1aea74c
Add new `--vid-stride` inference parameter for videos (#9256)
VELCpro Sep 4, 2022
32794c1
[pre-commit.ci] pre-commit suggestions (#9295)
pre-commit-ci[bot] Sep 6, 2022
5a134e0
Replace deprecated `np.int` with `int` (#9307)
glenn-jocher Sep 7, 2022
903b239
Comet Logging and Visualization Integration (#9232)
DN6 Sep 7, 2022
5f075ee
Comet changes (#9328)
DN6 Sep 8, 2022
3cd66b1
Train.py line 486 typo fix (#9330)
robinned Sep 8, 2022
8aa196c
Add dilated conv support (#9347)
YellowAndGreen Sep 9, 2022
24bf9cc
Update `check_requirements()` single install (#9353)
glenn-jocher Sep 10, 2022
e9ddc5b
Update `check_requirements(args, cmds='')` (#9355)
glenn-jocher Sep 10, 2022
57ef676
Update `check_requirements()` multiple string (#9356)
glenn-jocher Sep 10, 2022
e3e5122
Add PaddlePaddle export and inference (#9240)
kisaragychihaya Sep 10, 2022
4e8504a
PaddlePaddle Usage examples (#9358)
glenn-jocher Sep 10, 2022
2b5c9a8
labels.jpg names fix (#9361)
glenn-jocher Sep 10, 2022
cafdd18
Exclude `ipython` from hubconf.py `check_requirements()` (#9362)
glenn-jocher Sep 10, 2022
23d0456
`torch.jit.trace()` fix (#9363)
glenn-jocher Sep 10, 2022
23701ea
AMP Check fix (#9367)
glenn-jocher Sep 11, 2022
a4ed988
Remove duplicate line in setup.cfg (#9380)
zldrobit Sep 13, 2022
1323b48
Remove `.train()` mode exports (#9429)
glenn-jocher Sep 15, 2022
36cb05b
Continue on Docker arm64 failure (#9430)
glenn-jocher Sep 15, 2022
65afaa7
Continue on Docker failure (all backends) (#9432)
glenn-jocher Sep 15, 2022
abea53e
Continue on Docker fail (all backends) fix (#9433)
glenn-jocher Sep 15, 2022
f9869f7
YOLOv5 segmentation model support (#9052)
AyushExel Sep 15, 2022
58ad5ca
Fix val.py zero-TP bug (#9431)
glenn-jocher Sep 15, 2022
a1e5f9a
New model.yaml `activation:` field (#9371)
glenn-jocher Sep 15, 2022
c7a2d6b
Fix tick labels for background FN/FP (#9414)
hotohoto Sep 16, 2022
03f2ca8
Fix TensorRT exports to ONNX opset 12 (#9441)
glenn-jocher Sep 16, 2022
2ac4b63
AutoShape explicit arguments fix (#9443)
glenn-jocher Sep 16, 2022
fe10b4a
Update Detections() instance printing (#9445)
glenn-jocher Sep 16, 2022
db06f49
AutoUpdate TensorFlow in export.py (#9447)
glenn-jocher Sep 16, 2022
5e1a955
AutoBatch `cudnn.benchmark=True` fix (#9448)
glenn-jocher Sep 16, 2022
4a43080
Do not move downloaded zips (#9455)
glenn-jocher Sep 17, 2022
6a9fffd
Update general.py (#9454)
glenn-jocher Sep 17, 2022
0608374
`Detect()` and `Segment()` fixes for CoreML and Paddle (#9458)
glenn-jocher Sep 17, 2022
afb9860
Add Paddle exports to benchmarks (#9459)
glenn-jocher Sep 17, 2022
e8a9c5a
Add `macos-latest` runner for CoreML benchmarks (#9453)
glenn-jocher Sep 17, 2022
8ae81a6
Fix cutout bug (#9452)
Oswells Sep 18, 2022
95cef1a
Optimize imports (#9464)
glenn-jocher Sep 18, 2022
dc42e6e
TensorRT SegmentationModel fix (#9465)
glenn-jocher Sep 18, 2022
4d50cd3
`Conv()` dilation argument fix (#9466)
glenn-jocher Sep 18, 2022
295c5e9
Update ClassificationModel default training `imgsz=224` (#9469)
glenn-jocher Sep 18, 2022
ca9c993
Standardize warnings with `WARNING ⚠️ ...` (#9467)
glenn-jocher Sep 18, 2022
92b5242
TensorFlow macOS AutoUpdate (#9471)
glenn-jocher Sep 18, 2022
120e27e
`classify/predict --save-txt` fix (#9478)
glenn-jocher Sep 18, 2022
fda8aa5
TensorFlow SegmentationModel support (#9472)
glenn-jocher Sep 18, 2022
f038ad7
AutoBatch report include reserved+allocated (#9491)
glenn-jocher Sep 19, 2022
868c0e9
Update Detect() grid init `for` loop (#9494)
glenn-jocher Sep 19, 2022
1164069
Accelerate video inference (#9487)
mucunwuxian Sep 19, 2022
0b724c5
Comet Image Logging Fix (#9498)
DN6 Sep 19, 2022
0171198
Fix visualization title bug (#9500)
glenn-jocher Sep 19, 2022
63368e7
Add paddle tips (#9502)
Zengyf-CVer Sep 19, 2022
095f601
Segmentation `polygons2masks_overlap()` in `np.int32` (#9493)
glenn-jocher Sep 20, 2022
f8b7463
Fix `random_perspective` param bug in segment (#9512)
FeiGeChuanShu Sep 20, 2022
e233c03
Remove `check_requirements('flatbuffers==1.12')` (#9514)
glenn-jocher Sep 20, 2022
bd35191
Fix TF Lite exports (#9517)
glenn-jocher Sep 20, 2022
c0d9713
TFLite fix 2 (#9518)
glenn-jocher Sep 20, 2022
77dcf55
FROM nvcr.io/nvidia/pytorch:22.08-py3 (#9520)
glenn-jocher Sep 20, 2022
6ebef28
Remove scikit-learn constraint on coremltools 6.0 (#9530)
glenn-jocher Sep 21, 2022
499a6bf
Update scikit-learn constraint per coremltools 6.0 (#9531)
glenn-jocher Sep 21, 2022
db68474
Update `coremltools>=6.0` (#9532)
glenn-jocher Sep 21, 2022
6f02847
Update albumentations (#9503)
glenn-jocher Sep 21, 2022
999482b
import re (#9535)
glenn-jocher Sep 21, 2022
489920a
TF.js fix (#9536)
glenn-jocher Sep 21, 2022
b25d5a7
Refactor dataset batch-size (#9551)
glenn-jocher Sep 22, 2022
30fa9b6
Add `--source screen` for screenshot inference (#9542)
zombob Sep 22, 2022
1320ce1
Update `is_url()` (#9566)
glenn-jocher Sep 23, 2022
d669a74
Detect.py supports running against a Triton container (#9228)
gaziqbal Sep 23, 2022
c8e5230
New `scale_segments()` function (#9570)
glenn-jocher Sep 24, 2022
f11a8a6
generator seed fix for DDP mAP drop (#9545)
Forever518 Sep 24, 2022
55fbac9
Update default GitHub assets (#9573)
glenn-jocher Sep 25, 2022
ee91dc9
Update requirements.txt comment https://pytorch.org/get-started/local…
davidamacey Sep 25, 2022
2787ad7
Add segment line predictions (#9571)
glenn-jocher Sep 25, 2022
966b0e0
TensorRT detect.py inference fix (#9581)
glenn-jocher Sep 25, 2022
639d82f
Update Comet links (#9587)
glenn-jocher Sep 25, 2022
9006b41
Add global YOLOv5_DATASETS_DIR (#9586)
glenn-jocher Sep 25, 2022
9f1cf8d
Add Paperspace Gradient badges (#9588)
glenn-jocher Sep 25, 2022
959a466
#YOLOVISION22 announcement (#9590)
glenn-jocher Sep 25, 2022
bfe052b
Bump actions/stale from 5 to 6 (#9595)
dependabot[bot] Sep 26, 2022
bd9c0c4
#YOLOVISION22 update (#9598)
glenn-jocher Sep 26, 2022
c4c0ee8
Apple MPS -> CPU NMS fallback strategy (#9600)
glenn-jocher Sep 26, 2022
a5748e4
Updated Segmentation and Classification usage (#9607)
glenn-jocher Sep 26, 2022
6b2c9d1
Update export.py Usage examples (#9609)
glenn-jocher Sep 26, 2022
1460e57
Fix `is_url('https://ultralytics.com')` (#9610)
glenn-jocher Sep 26, 2022
7314363
Add `results.save(save_dir='path', exist_ok=False)` (#9617)
glenn-jocher Sep 27, 2022
2373d54
NMS MPS device wrapper (#9620)
glenn-jocher Sep 27, 2022
799e3d0
Add SegmentationModel unsupported warning (#9632)
glenn-jocher Sep 28, 2022
0860e58
Disabled upload_dataset flag temporarily due to an artifact related b…
soumik12345 Sep 29, 2022
82bec4c
Add NVIDIA Jetson Nano Deployment tutorial (#9656)
glenn-jocher Sep 29, 2022
8a19437
Added cutout import from utils/augmentations.py to use Cutout Aug in …
senhorinfinito Oct 1, 2022
1158a50
Simplify val.py benchmark mode with speed mode (#9674)
glenn-jocher Oct 2, 2022
c98128f
Allow list for Comet artifact class 'names' field (#9654)
KristenKehrer Oct 2, 2022
68d654d
[pre-commit.ci] pre-commit suggestions (#9685)
pre-commit-ci[bot] Oct 4, 2022
e4398cf
TensorRT `--dynamic` fix (#9691)
glenn-jocher Oct 4, 2022
7f097dd
FROM nvcr.io/nvidia/pytorch:22.09-py3 (#9711)
glenn-jocher Oct 5, 2022
5ef69ef
Error in utils/segment/general `masks2segments()` (#9724)
paulguerrie Oct 6, 2022
209be93
Fix segment evolution keys (#9742)
glenn-jocher Oct 9, 2022
2f1eb21
Remove #YOLOVISION22 notice (#9751)
glenn-jocher Oct 10, 2022
7a69035
Update Loggers (#9760)
glenn-jocher Oct 12, 2022
85ae985
update mask2segments and saving results (#9785)
vladoossss Oct 12, 2022
16f87bb
HUB VOC fix (#9792)
glenn-jocher Oct 13, 2022
15b7565
Update hubconf.py local repo Usage example (#9803)
glenn-jocher Oct 13, 2022
2a19d07
Fix xView dataloaders import (#9807)
glenn-jocher Oct 14, 2022
df80e7c
Argoverse HUB fix (#9809)
glenn-jocher Oct 14, 2022
e42c89d
`smart_optimizer()` revert to weight with decay (#9817)
glenn-jocher Oct 16, 2022
e3ff780
Allow PyTorch Hub results to display in notebooks (#9825)
glenn-jocher Oct 17, 2022
acff977
Logger Cleanup (#9828)
glenn-jocher Oct 17, 2022
f1482b0
Remove ipython from `check_requirements` exclude list (#9841)
glenn-jocher Oct 18, 2022
010cd0d
Update HUBDatasetStats() usage examples (#9842)
glenn-jocher Oct 18, 2022
d0df6c8
Update ZipFile to context manager (#9843)
glenn-jocher Oct 18, 2022
c471001
Update README.md (#9846)
glenn-jocher Oct 18, 2022
6371de8
Webcam show fix (#9847)
glenn-jocher Oct 18, 2022
3b1a9d2
Fix OpenVINO Usage example (#9874)
glenn-jocher Oct 20, 2022
eef9057
ClearML Dockerfile fix (#9876)
glenn-jocher Oct 20, 2022
fba61e5
Windows Python 3.7 .isfile() fix (#9879)
SSTato Oct 24, 2022
54f49fa
Add TFLite Metadata to TFLite and Edge TPU models (#9903)
paradigmn Oct 25, 2022
8236d88
Created using Colaboratory
glenn-jocher Oct 25, 2022
a5d875a
Add `gnupg` to Dockerfile-cpu (#9932)
glenn-jocher Oct 26, 2022
f9bb984
Add ClearML minimum version requirement (#9933)
glenn-jocher Oct 26, 2022
32a9218
Update Comet Integrations table text (#9937)
glenn-jocher Oct 26, 2022
38e5aae
Update README.md (#9957)
glenn-jocher Oct 28, 2022
be9ef38
Update README.md (#9958)
glenn-jocher Oct 28, 2022
6db0fac
Update README.md (#9961)
glenn-jocher Oct 28, 2022
575055c
Switch from suffix checks to archive checks (#9963)
kalenmike Oct 28, 2022
6e544d5
FROM nvcr.io/nvidia/pytorch:22.10-py3 (#9966)
glenn-jocher Oct 29, 2022
a625f29
Full-size proto code (optional) (#9980)
glenn-jocher Oct 30, 2022
e704970
Update README.md (#9970)
glenn-jocher Oct 31, 2022
a83d2a5
Segmentation Tutorial (#9521)
paulguerrie Oct 31, 2022
49156eb
Fix `is_colab()` (#9994)
glenn-jocher Nov 1, 2022
cf99788
Check online twice on AutoUpdate (#9999)
glenn-jocher Nov 1, 2022
c55e2cd
Add `min_items` filter option (#9997)
glenn-jocher Nov 1, 2022
067ad9a
Improved `check_online()` robustness (#10000)
glenn-jocher Nov 1, 2022
82a5585
Fix `min_items` (#10001)
glenn-jocher Nov 1, 2022
02b8a4c
Update default `--epochs 100` (#10024)
glenn-jocher Nov 3, 2022
fde7758
YOLOv5 AutoCache Update (#10027)
glenn-jocher Nov 4, 2022
78ed31c
IoU `eps` adjustment (#10051)
glenn-jocher Nov 6, 2022
6ae3dff
Update get_coco.sh (#10057)
glenn-jocher Nov 6, 2022
58b3d07
[pre-commit.ci] pre-commit suggestions (#10068)
pre-commit-ci[bot] Nov 7, 2022
e00d02d
Use MNIST160 (#10069)
glenn-jocher Nov 7, 2022
0039870
Update Dockerfile keep default torch installation (#10071)
glenn-jocher Nov 7, 2022
86decb3
Add `ultralytics` pip package (#10103)
glenn-jocher Nov 9, 2022
892c4cd
AutoShape integer image-size fix (#10090)
janus-zheng Nov 9, 2022
c1fcfe8
YouTube Usage example comments (#10106)
glenn-jocher Nov 9, 2022
75728bb
Mapped project and name to ClearML (#10100)
thepycoder Nov 9, 2022
078059c
Update IoU functions (#10123)
glenn-jocher Nov 10, 2022
55e9516
Add Ultralytics HUB to README (#10070)
glenn-jocher Nov 10, 2022
7c3827a
Fix benchmark.py usage comment (#10131)
rusamentiaga Nov 11, 2022
f33718f
Update HUB banner image (#10134)
glenn-jocher Nov 11, 2022
abbfd69
Copy-Paste zero value fix (#10152)
glenn-jocher Nov 14, 2022
ea73386
Add Copy-Paste to `mosaic9()` (#10165)
glenn-jocher Nov 15, 2022
9dd40f0
Add `join_threads()` (#10086)
glenn-jocher Nov 15, 2022
5e03f5f
Fix dataloader filepath modification to perform replace only once and…
adumrewal Nov 15, 2022
166b9f2
fix: prevent logging config clobbering (#10133)
rkechols Nov 16, 2022
9057510
Filter PyTorch 1.13 UserWarnings (#10166)
triple-mu Nov 16, 2022
e40662f
Revert "fix: prevent logging config clobbering" (#10177)
glenn-jocher Nov 16, 2022
a9f895d
Apply make_divisible for ONNX models in Autoshape (#10172)
janus-zheng Nov 17, 2022
1510111
data.yaml `names.keys()` integer assert (#10190)
glenn-jocher Nov 17, 2022
ff6e6e3
Fix: try 2 - prevent logging config clobbering (#10192)
rkechols Nov 17, 2022
467a57f
Segment prediction labels normalization fix (#10205)
glenn-jocher Nov 18, 2022
241d798
Created using Colaboratory
glenn-jocher Nov 18, 2022
946765b
Created using Colaboratory
glenn-jocher Nov 18, 2022
74b3886
Simplify dataloader tqdm descriptions (#10210)
glenn-jocher Nov 18, 2022
0322bb3
New global `TQDM_BAR_FORMAT` (#10211)
glenn-jocher Nov 18, 2022
6f377f9
Feature/classification tutorial refactor (#10039)
paulguerrie Nov 18, 2022
0051615
Remove Colab notebook High-Memory notices (#10212)
glenn-jocher Nov 18, 2022
2ecaa96
Created using Colaboratory
glenn-jocher Nov 18, 2022
7fc7ed7
Created using Colaboratory
glenn-jocher Nov 18, 2022
23f43ce
Created using Colaboratory
glenn-jocher Nov 18, 2022
9bf1855
Revert `--save-txt` to default False (#10213)
glenn-jocher Nov 18, 2022
9bc6034
Add `--source screen` Usage example (#10215)
glenn-jocher Nov 18, 2022
9286336
Add `git` info to training checkpoints (#9655)
glenn-jocher Nov 19, 2022
0307954
Add git info to cls, seg checkpoints (#10217)
glenn-jocher Nov 19, 2022
6992dde
Update Comet preview image (#10220)
glenn-jocher Nov 19, 2022
40bb803
Scope gitpyhon import in `check_git_info()` (#10221)
glenn-jocher Nov 19, 2022
72cad39
Squeezenet reshape outputs fix (#10222)
glenn-jocher Nov 19, 2022
be348cc
Validate --task speed CPU fix (#10244)
glenn-jocher Nov 21, 2022
915bbf2
YOLOv5 v7.0 release updates (#10245)
glenn-jocher Nov 22, 2022
b32f67f
`--single-cls` segments fix (#10260)
glenn-jocher Nov 22, 2022
c9d47ae
Created using Colaboratory
glenn-jocher Nov 22, 2022
61ebf5e
Created using Colaboratory
glenn-jocher Nov 22, 2022
7398d2d
Created using Colaboratory
glenn-jocher Nov 22, 2022
bfa1f23
FROM nvcr.io/nvidia/pytorch:22.11-py3 (#10279)
glenn-jocher Nov 24, 2022
31c1f11
`bbox_iou()` optimizations (#10296)
glenn-jocher Nov 25, 2022
85f8379
README Segmentation Usage fixes (#10298)
glenn-jocher Nov 26, 2022
350e8eb
Fix SegmentationModel Usage (#10303)
glenn-jocher Nov 26, 2022
f9ca365
Ultralytics Live 1 - ClearML https://youtu.be/KS4weDInJYs (#10324)
glenn-jocher Nov 28, 2022
10c025d
Add README License section (#10327)
glenn-jocher Nov 28, 2022
e808f22
Eliminate unused `ConfusionMatrix.matrix()` method (#10309)
xiaohu2015 Nov 30, 2022
7f5724b
Correct Segmentation Comparison Plot (#10344)
glenn-jocher Nov 30, 2022
b412696
Fix & speed up segment plot (#10350)
Laughing-q Dec 1, 2022
028b7cd
fix_reading_nan_in_evolve (#10358)
mbenami Dec 1, 2022
185d475
Add DNN warning comment (#10368)
glenn-jocher Dec 1, 2022
1ce464f
Add docker info for ClearML remote execution (#10142)
thepycoder Dec 1, 2022
7845cea
Fix ClearML unconfigured error (#10369)
glenn-jocher Dec 1, 2022
d7955fe
Fix clearml args logging when training is launch with run() (#10359)
MSutt Dec 1, 2022
d1ffc3a
Create CITATION.cff (#10387)
glenn-jocher Dec 2, 2022
e96113e
Update CITATION.cff to version: v7.0 (#10389)
glenn-jocher Dec 2, 2022
a1b6e79
Revert TQDM bar format changes (#10343)
glenn-jocher Dec 2, 2022
9722e6f
`process_mask_native()` cleanup (#10366)
glenn-jocher Dec 3, 2022
5dc1ce4
Support `.txt` files as a line-by-line media list rather than streams…
democat3457 Dec 3, 2022
f8539a6
Allow users to specify how to override a ClearML Task (#10363)
thepycoder Dec 5, 2022
0a1fdcd
Add catch for misspelled `--task` (#10420)
leandervaneekelen Dec 6, 2022
0624384
[pre-commit.ci] pre-commit suggestions (#10409)
pre-commit-ci[bot] Dec 6, 2022
454dae1
Ultralytics Live Session 2 - Roboflow https://youtu.be/LKpuzZllNpA (#…
taliabender Dec 6, 2022
de81239
Add README App section (#10446)
glenn-jocher Dec 9, 2022
1607aec
Automatic README translation to Simplified Chinese (#10445)
glenn-jocher Dec 9, 2022
342fe05
docs: Added README."zh-CN".md translation via https://github.com/deph…
github-actions[bot] Dec 9, 2022
443ef7f
Modify a comment for OpenCV File I/O Functions (#10467)
developer0hye Dec 12, 2022
357cde9
add force_reload=True when loading model using torch hub (#10460)
developer0hye Dec 12, 2022
1752768
Fix Chinese README (#10465)
Nioolek Dec 13, 2022
1ae9194
Update Comet hyperlinks (#10500)
nerdyespresso Dec 15, 2022
b564c1f
Check `conf_thres` and `iou_thres` prior to use (#10515)
developer0hye Dec 17, 2022
8d65f9d
Support extensive shape for functions related to bounding box localiz…
developer0hye Dec 17, 2022
b2f94e8
Update to ONNX opset 17 (#10522)
glenn-jocher Dec 17, 2022
4362372
Update train.py (#10485)
GreatV Dec 17, 2022
2c35c1b
Limit detections without explicit if condition (#10502)
developer0hye Dec 18, 2022
b2a0f1c
Update `onnx>=1.12.0` (#10526)
glenn-jocher Dec 18, 2022
10e93d2
Set a seed of generator with an option for more randomness when train…
developer0hye Dec 19, 2022
5545ff3
Sort by confidence and remove excess boxes without explicit if (#10517)
developer0hye Dec 19, 2022
f72f0fe
Add Albumentation Default hyperparameter file (#10529)
pourmand1376 Dec 20, 2022
887d952
Created using Colaboratory
glenn-jocher Dec 21, 2022
c765b8c
Created using Colaboratory
glenn-jocher Dec 21, 2022
96a71b1
Created using Colaboratory
glenn-jocher Dec 21, 2022
2370a55
Bugfix: update dataloaders.py to fix "resize to 0" (#10558)
bobo0810 Dec 22, 2022
5f8054c
FROM nvcr.io/nvidia/pytorch:22.12-py3 (#10588)
glenn-jocher Dec 24, 2022
3c1afd9
ENV OMP_NUM_THREADS=1 (#10593)
glenn-jocher Dec 26, 2022
60cb102
This is a combination of 5 commits.
triple-mu Sep 4, 2022
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
278 changes: 0 additions & 278 deletions .github/README_cn.md

This file was deleted.

68 changes: 55 additions & 13 deletions .github/workflows/ci-testing.yml
Original file line number Diff line number Diff line change
Expand Up @@ -5,20 +5,21 @@ name: YOLOv5 CI

on:
push:
branches: [master]
branches: [ master ]
pull_request:
branches: [master]
branches: [ master ]
schedule:
- cron: '0 0 * * *' # runs at 00:00 UTC every day

jobs:
Benchmarks:
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest]
python-version: ['3.9'] # requires python<=3.9
model: [yolov5n]
os: [ ubuntu-latest ]
python-version: [ '3.9' ] # requires python<=3.9
model: [ yolov5n ]
steps:
- uses: actions/checkout@v3
- uses: actions/setup-python@v4
Expand All @@ -37,19 +38,28 @@ jobs:
python --version
pip --version
pip list
- name: Run benchmarks
- name: Benchmark DetectionModel
run: |
python benchmarks.py --data coco128.yaml --weights ${{ matrix.model }}.pt --img 320 --hard-fail 0.29
- name: Benchmark SegmentationModel
run: |
python utils/benchmarks.py --weights ${{ matrix.model }}.pt --img 320 --hard-fail
python benchmarks.py --data coco128-seg.yaml --weights ${{ matrix.model }}-seg.pt --img 320 --hard-fail 0.22
- name: Test predictions
run: |
python export.py --weights ${{ matrix.model }}-cls.pt --include onnx --img 224
python detect.py --weights ${{ matrix.model }}.onnx --img 320
python segment/predict.py --weights ${{ matrix.model }}-seg.onnx --img 320
python classify/predict.py --weights ${{ matrix.model }}-cls.onnx --img 224

Tests:
timeout-minutes: 60
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, macos-latest, windows-latest]
python-version: ['3.10']
model: [yolov5n]
os: [ ubuntu-latest, windows-latest ] # macos-latest bug https://github.com/ultralytics/yolov5/pull/9049
python-version: [ '3.10' ]
model: [ yolov5n ]
include:
- os: ubuntu-latest
python-version: '3.7' # '3.6.8' min
Expand Down Expand Up @@ -87,7 +97,7 @@ jobs:
else
pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cpu
fi
shell: bash # required for Windows compatibility
shell: bash # for Windows compatibility
- name: Check environment
run: |
python -c "import utils; utils.notebook_init()"
Expand All @@ -100,8 +110,8 @@ jobs:
python --version
pip --version
pip list
- name: Run tests
shell: bash
- name: Test detection
shell: bash # for Windows compatibility
run: |
# export PYTHONPATH="$PWD" # to run '$ python *.py' files in subdirectories
m=${{ matrix.model }} # official weights
Expand All @@ -119,7 +129,39 @@ jobs:
python export.py --weights $m.pt --img 64 --include torchscript # export
python - <<EOF
import torch
im = torch.zeros([1, 3, 64, 64])
for path in '$m', '$b':
model = torch.hub.load('.', 'custom', path=path, source='local')
print(model('data/images/bus.jpg'))
model(im) # warmup, build grids for trace
torch.jit.trace(model, [im])
EOF
- name: Test segmentation
shell: bash # for Windows compatibility
run: |
m=${{ matrix.model }}-seg # official weights
b=runs/train-seg/exp/weights/best # best.pt checkpoint
python segment/train.py --imgsz 64 --batch 32 --weights $m.pt --cfg $m.yaml --epochs 1 --device cpu # train
python segment/train.py --imgsz 64 --batch 32 --weights '' --cfg $m.yaml --epochs 1 --device cpu # train
for d in cpu; do # devices
for w in $m $b; do # weights
python segment/val.py --imgsz 64 --batch 32 --weights $w.pt --device $d # val
python segment/predict.py --imgsz 64 --weights $w.pt --device $d # predict
python export.py --weights $w.pt --img 64 --include torchscript --device $d # export
done
done
- name: Test classification
shell: bash # for Windows compatibility
run: |
m=${{ matrix.model }}-cls.pt # official weights
b=runs/train-cls/exp/weights/best.pt # best.pt checkpoint
python classify/train.py --imgsz 32 --model $m --data mnist160 --epochs 1 # train
python classify/val.py --imgsz 32 --weights $b --data ../datasets/mnist160 # val
python classify/predict.py --imgsz 32 --weights $b --source ../datasets/mnist160/test/7/60.png # predict
python classify/predict.py --imgsz 32 --weights $m --source data/images/bus.jpg # predict
python export.py --weights $b --img 64 --include torchscript # export
python - <<EOF
import torch
for path in '$m', '$b':
model = torch.hub.load('.', 'custom', path=path, source='local')
EOF
3 changes: 3 additions & 0 deletions .github/workflows/docker.yml
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@ jobs:

- name: Build and push arm64 image
uses: docker/build-push-action@v3
continue-on-error: true
with:
context: .
platforms: linux/arm64
Expand All @@ -39,6 +40,7 @@ jobs:

- name: Build and push CPU image
uses: docker/build-push-action@v3
continue-on-error: true
with:
context: .
file: utils/docker/Dockerfile-cpu
Expand All @@ -47,6 +49,7 @@ jobs:

- name: Build and push GPU image
uses: docker/build-push-action@v3
continue-on-error: true
with:
context: .
file: utils/docker/Dockerfile
Expand Down
22 changes: 8 additions & 14 deletions .github/workflows/greetings.yml
Original file line number Diff line number Diff line change
Expand Up @@ -17,16 +17,10 @@ jobs:
repo-token: ${{ secrets.GITHUB_TOKEN }}
pr-message: |
👋 Hello @${{ github.actor }}, thank you for submitting a YOLOv5 🚀 PR! To allow your work to be integrated as seamlessly as possible, we advise you to:
- ✅ Verify your PR is **up-to-date with upstream/master.** If your PR is behind upstream/master an automatic [GitHub Actions](https://github.com/ultralytics/yolov5/blob/master/.github/workflows/rebase.yml) merge may be attempted by writing /rebase in a new comment, or by running the following code, replacing 'feature' with the name of your local branch:
```bash
git remote add upstream https://github.com/ultralytics/yolov5.git
git fetch upstream
# git checkout feature # <--- replace 'feature' with local branch name
git merge upstream/master
git push -u origin -f
```
- ✅ Verify all Continuous Integration (CI) **checks are passing**.
- ✅ Reduce changes to the absolute **minimum** required for your bug fix or feature addition. _"It is not daily increase but daily decrease, hack away the unessential. The closer to the source, the less wastage there is."_ -Bruce Lee

- ✅ Verify your PR is **up-to-date** with `ultralytics/yolov5` `master` branch. If your PR is behind you can update your code by clicking the 'Update branch' button or by running `git pull` and `git merge master` locally.
- ✅ Verify all YOLOv5 Continuous Integration (CI) **checks are passing**.
- ✅ Reduce changes to the absolute **minimum** required for your bug fix or feature addition. _"It is not daily increase but daily decrease, hack away the unessential. The closer to the source, the less wastage there is."_ — Bruce Lee

issue-message: |
👋 Hello @${{ github.actor }}, thank you for your interest in YOLOv5 🚀! Please visit our ⭐️ [Tutorials](https://github.com/ultralytics/yolov5/wiki#tutorials) to get started, where you can find quickstart guides for simple tasks like [Custom Data Training](https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data) all the way to advanced concepts like [Hyperparameter Evolution](https://github.com/ultralytics/yolov5/issues/607).
Expand All @@ -50,14 +44,14 @@ jobs:

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled):

- **Google Colab and Kaggle** notebooks with free GPU: <a href="https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> <a href="https://www.kaggle.com/ultralytics/yolov5"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open In Kaggle"></a>
- **Notebooks** with free GPU: <a href="https://bit.ly/yolov5-paperspace-notebook"><img src="https://assets.paperspace.io/img/gradient-badge.svg" alt="Run on Gradient"></a> <a href="https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> <a href="https://www.kaggle.com/ultralytics/yolov5"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open In Kaggle"></a>
- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart)
- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart)
- **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) <a href="https://hub.docker.com/r/ultralytics/yolov5"><img src="https://img.shields.io/docker/pulls/ultralytics/yolov5?logo=docker" alt="Docker Pulls"></a>


## Status

<a href="https://github.com/ultralytics/yolov5/actions/workflows/ci-testing.yml"><img src="https://github.com/ultralytics/yolov5/actions/workflows/ci-testing.yml/badge.svg" alt="CI CPU testing"></a>
<a href="https://github.com/ultralytics/yolov5/actions/workflows/ci-testing.yml"><img src="https://github.com/ultralytics/yolov5/actions/workflows/ci-testing.yml/badge.svg" alt="YOLOv5 CI"></a>

If this badge is green, all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 [training](https://github.com/ultralytics/yolov5/blob/master/train.py), [validation](https://github.com/ultralytics/yolov5/blob/master/val.py), [inference](https://github.com/ultralytics/yolov5/blob/master/detect.py), [export](https://github.com/ultralytics/yolov5/blob/master/export.py) and [benchmarks](https://github.com/ultralytics/yolov5/blob/master/benchmarks.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

If this badge is green, all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training ([train.py](https://github.com/ultralytics/yolov5/blob/master/train.py)), validation ([val.py](https://github.com/ultralytics/yolov5/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov5/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov5/blob/master/export.py)) on macOS, Windows, and Ubuntu every 24 hours and on every commit.
21 changes: 0 additions & 21 deletions .github/workflows/rebase.yml

This file was deleted.

2 changes: 1 addition & 1 deletion .github/workflows/stale.yml
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ jobs:
stale:
runs-on: ubuntu-latest
steps:
- uses: actions/stale@v5
- uses: actions/stale@v6
with:
repo-token: ${{ secrets.GITHUB_TOKEN }}
stale-issue-message: |
Expand Down
26 changes: 26 additions & 0 deletions .github/workflows/translate-readme.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# README translation action to translate README.md to Chinese as README.zh-CN.md on any change to README.md

name: Translate README

on:
push:
branches:
- translate_readme # replace with 'master' to enable action
paths:
- README.md

jobs:
Translate:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- name: Setup Node.js
uses: actions/setup-node@v3
with:
node-version: 16
# ISO Langusge Codes: https://cloud.google.com/translate/docs/languages
- name: Adding README - Chinese Simplified
uses: dephraiim/translate-readme@main
with:
LANG: zh-CN
12 changes: 6 additions & 6 deletions .pre-commit-config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ ci:

repos:
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v4.3.0
rev: v4.4.0
hooks:
# - id: end-of-file-fixer
- id: trailing-whitespace
Expand All @@ -24,7 +24,7 @@ repos:
- id: check-docstring-first

- repo: https://github.com/asottile/pyupgrade
rev: v2.37.3
rev: v3.3.0
hooks:
- id: pyupgrade
name: Upgrade code
Expand All @@ -43,22 +43,22 @@ repos:
name: YAPF formatting

- repo: https://github.com/executablebooks/mdformat
rev: 0.7.14
rev: 0.7.16
hooks:
- id: mdformat
name: MD formatting
additional_dependencies:
- mdformat-gfm
- mdformat-black
exclude: "README.md|README_cn.md"
exclude: "README.md|README.zh-CN.md"

- repo: https://github.com/asottile/yesqa
rev: v1.3.0
rev: v1.4.0
hooks:
- id: yesqa

- repo: https://github.com/PyCQA/flake8
rev: 5.0.2
rev: 6.0.0
hooks:
- id: flake8
name: PEP8
14 changes: 14 additions & 0 deletions CITATION.cff
Original file line number Diff line number Diff line change
@@ -0,0 +1,14 @@
cff-version: 1.2.0
preferred-citation:
type: software
message: If you use YOLOv5, please cite it as below.
authors:
- family-names: Jocher
given-names: Glenn
orcid: "https://orcid.org/0000-0001-5950-6979"
title: "YOLOv5 by Ultralytics"
version: 7.0
doi: 10.5281/zenodo.3908559
date-released: 2020-5-29
license: GPL-3.0
url: "https://github.com/ultralytics/yolov5"
23 changes: 9 additions & 14 deletions CONTRIBUTING.md
Original file line number Diff line number Diff line change
Expand Up @@ -45,20 +45,15 @@ changes** button. All done, your PR is now submitted to YOLOv5 for review and ap

To allow your work to be integrated as seamlessly as possible, we advise you to:

- ✅ Verify your PR is **up-to-date with upstream/master.** If your PR is behind upstream/master an
automatic [GitHub Actions](https://github.com/ultralytics/yolov5/blob/master/.github/workflows/rebase.yml) merge may
be attempted by writing /rebase in a new comment, or by running the following code, replacing 'feature' with the name
of your local branch:

```bash
git remote add upstream https://github.com/ultralytics/yolov5.git
git fetch upstream
# git checkout feature # <--- replace 'feature' with local branch name
git merge upstream/master
git push -u origin -f
```

- ✅ Verify all Continuous Integration (CI) **checks are passing**.
- ✅ Verify your PR is **up-to-date** with `ultralytics/yolov5` `master` branch. If your PR is behind you can update
your code by clicking the 'Update branch' button or by running `git pull` and `git merge master` locally.

<p align="center"><img width="751" alt="Screenshot 2022-08-29 at 22 47 15" src="https://user-images.githubusercontent.com/26833433/187295893-50ed9f44-b2c9-4138-a614-de69bd1753d7.png"></p>

- ✅ Verify all YOLOv5 Continuous Integration (CI) **checks are passing**.

<p align="center"><img width="751" alt="Screenshot 2022-08-29 at 22 47 03" src="https://user-images.githubusercontent.com/26833433/187296922-545c5498-f64a-4d8c-8300-5fa764360da6.png"></p>

- ✅ Reduce changes to the absolute **minimum** required for your bug fix or feature addition. _"It is not daily increase
but daily decrease, hack away the unessential. The closer to the source, the less wastage there is."_ — Bruce Lee

Expand Down
Loading