Papers › YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

6 Jul 2022CVPR 2023 1arXiv:2207.02696archive 2025-07-28

Chien-Yao Wang, Alexey Bochkovskiy, Hong-Yuan Mark Liao

YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS and has the highest accuracy 56.8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100. YOLOv7-E6 object detector (56 FPS V100, 55.9% AP) outperforms both transformer-based detector SWIN-L Cascade-Mask R-CNN (9.2 FPS A100, 53.9% AP) by 509% in speed and 2% in accuracy, and convolutional-based detector ConvNeXt-XL Cascade-Mask R-CNN (8.6 FPS A100, 55.2% AP) by 551% in speed and 0.7% AP in accuracy, as well as YOLOv7 outperforms: YOLOR, YOLOX, Scaled-YOLOv4, YOLOv5, DETR, Deformable DETR, DINO-5scale-R50, ViT-Adapter-B and many other object detectors in speed and accuracy. Moreover, we train YOLOv7 only on MS COCO dataset from scratch without using any other datasets or pre-trained weights. Source code is released in https://github.com/WongKinYiu/yolov7.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2207.02696")

Code

Syntology Ran 1 of 11 code samples harvested from 3 repositories linked to this paper; 10 have no recorded run. Of those that ran: 1 ran · honoured contract.

By repository: community (archive-listed): 11 samples from 3 repositories, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

21 repositories listed; official and paper-mentioned ones first.

wongkinyiu/yolov7 officialmentioned in papermentioned on GitHubpytorchGPL-3.0 report
AlexeyAB/darknet mentioned on GitHubtfNOASSERTION report
LdDl/rust-road-traffic mentioned on GitHubApache-2.0 report
WongKinYiu/YOLO mentioned on GitHubpytorchMIT report
dnozza/profanity-obfuscation mentioned on GitHubMIT report
henrytsui000/YOLO mentioned on GitHubpytorch report
mikel-brostrom/yolov7 mentioned on GitHubpytorchGPL-3.0 report
mkang315/rcs-yolo mentioned on GitHubpytorch report
ogatarina-sq/secyolov7 mentioned on GitHubpytorchGPL-3.0 report
pjreddie/darknet mentioned on GitHubpytorchNOASSERTION report
xinwei666/mmgenerativeir mentioned on GitHubpytorch report
zhanghuiyao/yolov7_mindspore mentioned on GitHubmindsporeMIT report
open-mmlab/mmyolo pytorchGPL-3.0 report
securade/hub pytorchAGPL-3.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested; 1 ran; 1 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
10unverified

Licence: 0 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

autopad kadirnar/yolov7-pip/yolov7/models/common.py community (archive-listed) ran · honoured contract MIT (permissive) · 988a3c854b1b13d0 · report
DWConv kadirnar/yolov7-pip/yolov7/models/common.py community (archive-listed) unverified MIT (permissive) · b9a38c519e71eeba · report
compare_version zhanghuiyao/yolov7_mindspore/utils/all_finite.py community (archive-listed) unverified MIT (permissive) · d6ae8e6a9c267f7b · report
compute_iou ibaiGorordo/ONNX-YOLOv7-Object-Detection/yolov7/utils.py community (archive-listed) unverified MIT (permissive) · 21a47905e98284b9 · report
load_image zhanghuiyao/yolov7_mindspore/utils/augumentations.py community (archive-listed) unverified MIT (permissive) · 96c97809b6f786f8 · report
make_divisible zhanghuiyao/yolov7_mindspore/network/common.py community (archive-listed) unverified MIT (permissive) · c609b51715f9ac43 · report
nms ibaiGorordo/ONNX-YOLOv7-Object-Detection/yolov7/utils.py community (archive-listed) unverified MIT (permissive) · ac863afc480b7414 · report
sigmoid zhanghuiyao/yolov7_mindspore/postprocess.py community (archive-listed) unverified MIT (permissive) · e9b5f76a6fafe2ee · report
smooth_BCE kadirnar/yolov7-pip/yolov7/utils/loss.py community (archive-listed) unverified MIT (permissive) · 386a04c4b6c96c88 · report
transI_fusebn kadirnar/yolov7-pip/yolov7/models/common.py community (archive-listed) unverified MIT (permissive) · 079d0a85a0bfbb47 · report
xywh2xyxy ibaiGorordo/ONNX-YOLOv7-Object-Detection/yolov7/utils.py community (archive-listed) unverified MIT (permissive) · 2b72f89bf58c2228 · report

Tasks

2D Object DetectionObjectObject DetectionPedestrian DetectionReal-Time Object DetectionVideo Object Tracking

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Object Detection CeyMo YOLOv7 mAP 69.5 #2 of 5 Archive leaderboard report
Object Detection COCO test-dev YOLOv7-D6 (44 fps) box mAP 56.6 #40 of 225 Archive leaderboard report
Object Detection COCO test-dev YOLOv7-E6 (56 fps) box mAP 56 #46 of 225 Archive leaderboard report
Object Detection COCO test-dev YOLOv7-W6 (84 fps) box mAP 54.9 #51 of 225 Archive leaderboard report
Object Detection COCO test-dev YOLOv7-X (114 fps) box mAP 53.1 #67 of 225 Archive leaderboard report
Object Detection COCO test-dev YOLOv7 (161 fps) box mAP 51.4 #80 of 225 Archive leaderboard report
Object Detection COCO-O YOLOv7-E6E Average mAP 32.0 #15 of 45 Archive leaderboard report
Object Detection COCO-O YOLOv7-E6E Effective Robustness 6.42 #15 of 45 Archive leaderboard report
Pedestrian Detection DVTOD YOLOv7 (Thermal) mAP 77.8 #7 of 8 Archive leaderboard report
Pedestrian Detection DVTOD YOLOv7 (Visible) mAP 35.3 #8 of 8 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv7-E6E(1280) FPS (V100, b=1) 36 #6 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv7-E6E(1280) box AP 56.8 #6 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv7-D6(1280) FPS (V100, b=1) 44 #7 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv7-D6(1280) box AP 56.6 #7 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv7-E6(1280) FPS (V100, b=1) 56 #10 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv7-E6(1280) box AP 56 #10 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv7-W6(1280) FPS (V100, b=1) 84 #17 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv7-W6(1280) box AP 54.9 #17 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv7-X FPS (V100, b=1) 114 #32 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv7-X box AP 53.1 #32 of 82 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationCSPDarknet53ConvolutionDeformable Attention ModuleDeformable DETRGlobal Average PoolingResidual ConnectionSPEEDSoftmaxYOLOX

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections