Student or educator? Sign up with your school email and get 6 months of Pro free.

The DOI matches its DataCite record.

ultralytics/yolov5: v3.0

Open access
Jocher, Glenn, Stoken, Alex, Borovec, Jirka, NanoCode012, ChristopherSTAN, Changyu, Liu, Laughing, Hogan, Adam, Lorenzomammana, Tkianai, YxNONG, AlexWang1900, Diaconu, Laurentiu, , Marc, Wanghaoyang0106, Ml5ah, , Doug, Hatovix, Poznanski, Jake, Lijun Yu 于力军, Changyu98, Rai, Prashant, Ferriday, Russ, Sullivan, Trevor, Xinyu, Wang, YuriRibeiro, Claramunt, Eduard Reñé, Hopesala, Pritul Dave, Yzchen · 2020 · Zenodo

Abstract

Breaking Changes This release does not contain breaking changes. Bug Fixes Hyperparameter evolution fixed, tutorial added (https://github.com/ultralytics/yolov5/issues/607) Added Functionality PyTorch 1.6 native AMP replaces NVIDIA Apex AMP (https://github.com/ultralytics/yolov5/pull/573) nn.Hardswish() activations replace nn.LeakyReLU(0.1) in base convolution module models.Conv() Dataset Autodownload feature added (https://github.com/ultralytics/yolov5/pull/685) Model Autodownload improved (https://github.com/ultralytics/yolov5/pull/711) Layer freezing code added (https://github.com/ultralytics/yolov5/issues/679) TensorRT export tutorial added (https://github.com/ultralytics/yolov5/pull/623) ** GPU Speed measures end-to-end time per image averaged over 5000 COCO val2017 images using a V100 GPU with batch size 8, and includes image preprocessing, PyTorch FP16 inference, postprocessing and NMS. August 13, 2020: v3.0 release: nn.Hardswish() activations, data autodownload, native AMP. July 23, 2020: v2.0 release: improved model definition, training and mAP. June 22, 2020: PANet updates: new heads, reduced parameters, improved speed and mAP 364fcfd. June 19, 2020: FP16 as new default for smaller checkpoints and faster inference d4c6674. June 9, 2020: CSP updates: improved speed, size, and accuracy (credit to @WongKinYiu for CSP). May 27, 2020: Public release. YOLOv5 models are SOTA among all known YOLO implementations. April 1, 2020: Start development of future compound-scaled YOLOv3/YOLOv4-based PyTorch models. Pretrained Checkpoints v3.0 with nn.Hardswish() Model AP val AP test AP 50 Speed GPU FPS GPU params FLOPS YOLOv5s 37.0 37.0 56.2 2.4ms 476 7.5M 13.2B YOLOv5m 44.3 44.3 63.2 3.4ms 333 21.8M 39.4B YOLOv5l 47.7 47.7 66.5 4.4ms 256 47.8M 88.1B YOLOv5x 49.2 49.2 67.7 6.9ms 164 89.0M 166.4B YOLOv5x + TTA 50.8 50.8 68.9 25.5ms 39 89.0M 354.3B YOLOv3-SPP 45.6 45.5 65.2 4.5ms 222 63.0M 118.0B AP test denotes COCO test-dev2017 server results, all other AP results in the table denote val2017 accuracy. All AP numbers are for single-model single-scale without ensemble or test-time augmentation. Reproduce by python test.py --data coco.yaml --img 640 --conf 0.001 Speed GPU measures end-to-end time per image averaged over 5000 COCO val2017 images using a GCP n1-standard-16 instance with one V100 GPU, and includes image preprocessing, PyTorch FP16 image inference at --batch-size 32 --img-size 640, postprocessing and NMS. Average NMS time included in this chart is 1-2ms/img. Reproduce by python test.py --data coco.yaml --img 640 --conf 0.1 All checkpoints are trained to 300 epochs with default settings and hyperparameters (no autoaugmentation). Test Time Augmentation (TTA) runs at 3 image sizes. Reproduce** by python test.py --data coco.yaml --img 832 --augment v2.0 with nn.LeakyReLU(0.1) Model AP val AP test AP 50 Speed GPU FPS GPU params FLOPS YOLOv5s 36.1 36.1 55.3 2.2ms 476 7.5M 13.2B YOLOv5m 43.5 43.5 62.5 3.2ms 333 21.8M 39.4B YOLOv5l 47.0 47.1 65.6 4.1ms 256 47.8M 88.1B YOLOv5x 49.0 49.0 67.4 6.4ms 164 89.0M 166.4B YOLOv5x + TTA 50.4 50.4 68.5 23.4ms 43 89.0M 354.3B YOLOv3-SPP 45.6 45.5 65.2 4.5ms 222 63.0M 118.0B AP test denotes COCO test-dev2017 server results, all other AP results in the table denote val2017 accuracy. All AP numbers are for single-model single-scale without ensemble or test-time augmentation. Reproduce by python test.py --data coco.yaml --img 672 --conf 0.001 Speed GPU measures end-to-end time per image averaged over 5000 COCO val2017 images using a GCP n1-standard-16 instance with one V100 GPU, and includes image preprocessing, PyTorch FP16 image inference at --batch-size 32 --img-size 640, postprocessing and NMS. Average NMS time included in this chart is 1-2ms/img. Reproduce by python test.py --data coco.yaml --img 640 --conf 0.1 All checkpoints are trained to 300 epochs with default settings and hyperparameters (no autoaugmentation).

Overview

Integrity signals

Registry

DataCite · 10.5281/zenodo.3983579

Cites

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

The text we found for this paper looks like another document, so its claims and self-check weren’t run. The registry and citation checks still apply.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The text we found for this paper looks like another document, so the self-check wasn’t run.

Citations

Cites

Still being checked.

Cited by

See all 2,738

Metadata

Authors
Jocher, G., Stoken, A., Borovec, J., NanoCode012, ChristopherSTAN, Changyu, L., Laughing, Hogan, A., Lorenzomammana, Tkianai, YxNONG, AlexWang1900, Diaconu, L., M., Wanghaoyang0106, Ml5ah, D., Hatovix, Poznanski, J., 于力军, L. Y., Changyu98, Rai, P., Ferriday, R., Sullivan, T., Xinyu, W., YuriRibeiro, Claramunt, E. R., Hopesala, Dave, P., & Yzchen
Affiliations
  • @ultralytics
  • Johnson Space Center (US)
  • Czech Technical University in Prague (CZ)
  • Alibaba Group (United States) (US)
  • University of Milano-Bicocca (IT)
  • 玻璃杯哲学
  • innAIte technologies
  • Carnegie Mellon University (US)
  • Topia Systems Ltd
  • Digitalist @digitalist-se
  • Harbin Institute of Technology (CN)
  • Shanghai Jiao Tong University (CN)
Venue
Zenodo
Publisher
Zenodo
Published
2020-08-13
OpenAlex
W6893711219
Cited by
2,738
References
0
Citations by year
2026: 227 · 2025: 534 · 2024: 681 · 2023: 759 · 2022: 370 · 2021: 161 · 2020: 6
Type
software
Language
en
Open access
Licence
other-oa
Locations
  • Zenodo (CERN European Organization for Nuclear Research) (submittedVersion, other-oa)
  • Zenodo (CERN European Organization for Nuclear Research) (other-oa)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Life Sciences › Agricultural and Biological Sciences › Plant Science › Smart Agriculture and AI
Keywords
instance segmentation, real-time object detection

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: ultralytics/yolov5: v3.0. https://app.cochat.ai/papers/10.5281/zenodo.3983579
The paper
Jocher, G., Stoken, A., Borovec, J., NanoCode012, ChristopherSTAN, Changyu, L., Laughing, Hogan, A., Lorenzomammana, Tkianai, YxNONG, AlexWang1900, Diaconu, L., M., Wanghaoyang0106, Ml5ah, D., Hatovix, Poznanski, J., . . . Yzchen. (2020). ultralytics/yolov5: v3.0. Zenodo. https://doi.org/10.5281/zenodo.3983579

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.