Download Latest Version
v7.0 - YOLOv5 SOTA Realtime Instance Segmentation source code.zip (1.0 MB)
Get an email when there's a new version of YOLOv5
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| yolov5s-fp16-256x320.tflite | 2021-12-23 | 14.6 MB | |
| yolov5s-fp16-320x192.tflite | 2021-12-13 | 14.6 MB | |
| yolov5n-fp16-320.tflite | 2021-12-08 | 3.8 MB | |
| yolov5m-fp16-320.tflite | 2021-12-08 | 42.5 MB | |
| yolov5s-fp16-320.tflite | 2021-12-08 | 14.6 MB | |
| yolov5x-fp16-320.tflite | 2021-12-08 | 173.6 MB | |
| yolov5l-fp16-320.tflite | 2021-12-08 | 93.3 MB | |
| yolov5x.onnx | 2021-12-01 | 346.9 MB | |
| yolov5s.onnx | 2021-12-01 | 28.9 MB | |
| yolov5n.onnx | 2021-12-01 | 7.5 MB | |
| yolov5m.onnx | 2021-12-01 | 84.7 MB | |
| yolov5l.onnx | 2021-12-01 | 186.2 MB | |
| yolov5x.mlmodel | 2021-12-01 | 87.1 MB | |
| yolov5s.mlmodel | 2021-12-01 | 7.5 MB | |
| yolov5n.mlmodel | 2021-12-01 | 2.1 MB | |
| yolov5m.mlmodel | 2021-12-01 | 21.5 MB | |
| yolov5l.mlmodel | 2021-12-01 | 46.9 MB | |
| yolov5m_Objects365.pt | 2021-10-23 | 45.1 MB | |
| yolov5n.pt | 2021-10-13 | 4.0 MB | |
| README.md | 2021-10-12 | 62.9 kB | |
| v6.0 - YOLOv5n _Nano_ models, Roboflow integration, TensorFlow export, OpenCV DNN support.tar.gz | 2021-10-12 | 817.5 kB | |
| v6.0 - YOLOv5n _Nano_ models, Roboflow integration, TensorFlow export, OpenCV DNN support.zip | 2021-10-12 | 867.0 kB | |
| yolov5x6.pt | 2021-10-11 | 282.4 MB | |
| yolov5m.pt | 2021-10-11 | 42.7 MB | |
| yolov5x.pt | 2021-10-11 | 174.0 MB | |
| yolov5l.pt | 2021-10-11 | 93.5 MB | |
| yolov5s.pt | 2021-10-11 | 14.7 MB | |
| yolov5m6.pt | 2021-10-11 | 72.0 MB | |
| yolov5n6.pt | 2021-10-11 | 6.9 MB | |
| yolov5s6.pt | 2021-10-11 | 25.7 MB | |
| yolov5l6.pt | 2021-10-11 | 154.2 MB | |
| Totals: 31 Items | 2.1 GB | 17 | |
This release incorporates many new features and bug fixes (465 PRs from 73 contributors) since our last release v5.0 in April, brings architecture tweaks, and also introduces new P5 and P6 'Nano' models: YOLOv5n and YOLOv5n6. Nano models maintain the YOLOv5s depth multiple of 0.33 but reduce the YOLOv5s width multiple from 0.50 to 0.25, resulting in ~75% fewer parameters, from 7.5M to 1.9M, ideal for mobile and CPU solutions.
Example usage:
:::bash
python detect.py --weights yolov5n.pt --img 640 # Nano P5 model trained at --img 640 (28.4 mAP@0.5:0.95)
python detect.py --weights yolov5n6.pt --img 1280 # Nano P6 model trained at --img 1280 (34.0 mAP0.5:0.95)
Important Updates
-
Roboflow Integration ⭐ NEW: Train YOLOv5 models directly on any Roboflow dataset with our new integration! (https://github.com/ultralytics/yolov5/issues/4975 by @Jacobsolawetz)
-
YOLOv5n 'Nano' models ⭐ NEW: New smaller YOLOv5n (1.9M params) model below YOLOv5s (7.5M params), exports to 2.1 MB INT8 size, ideal for ultralight mobile solutions. (https://github.com/ultralytics/yolov5/discussions/5027 by @glenn-jocher)
- TensorFlow and Keras Export: TensorFlow, Keras, TFLite, TF.js model export now fully integrated using
python export.py --include saved_model pb tflite tfjs(https://github.com/ultralytics/yolov5/pull/1127 by @zldrobit) - OpenCV DNN: YOLOv5 ONNX models are now compatible with both OpenCV DNN and ONNX Runtime (https://github.com/ultralytics/yolov5/pull/4833 by @SamFC10).
- Model Architecture: Updated backbones are slightly smaller, faster and more accurate.
- Replacement of
Focus()with an equivalentConv(k=6, s=2, p=2)layer (https://github.com/ultralytics/yolov5/issues/4825 by @thomasbi1) for improved exportability - New
SPPF()replacement forSPP()layer for reduced ops (https://github.com/ultralytics/yolov5/pull/4420 by @glenn-jocher) - Reduction in P3 backbone layer
C3()repeats from 9 to 6 for improved speeds - Reorder places
SPPF()at end of backbone - Reintroduction of shortcut in the last
C3()backbone layer - Updated hyperparameters with increased mixup and copy-paste augmentation
New Results
YOLOv5-P5 640 Figure (click to expand)
Figure Notes (click to expand)
* **COCO AP val** denotes mAP@0.5:0.95 metric measured on the 5000-image [COCO val2017](http://cocodataset.org) dataset over various inference sizes from 256 to 1536. * **GPU Speed** measures average inference time per image on [COCO val2017](http://cocodataset.org) dataset using a [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/) V100 instance at batch-size 32. * **EfficientDet** data from [google/automl](https://github.com/google/automl) at batch size 8. * **Reproduce** by `python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n6.pt yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt`mAP improves from +0.3% to +1.1% across all models, and ~5% FLOPs reduction produces slight speed improvements and a reduced CUDA memory footprint. Example YOLOv5l before and after metrics:
| YOLOv5l Large |
size (pixels) |
mAPval 0.5:0.95 |
mAPval 0.5 |
Speed CPU b1 (ms) |
Speed V100 b1 (ms) |
Speed V100 b32 (ms) |
params (M) |
FLOPs @640 (B) |
|---|---|---|---|---|---|---|---|---|
| v5.0 (previous) | 640 | 48.2 | 66.9 | 457.9 | 11.6 | 2.8 | 47.0 | 115.4 |
| v6.0 (this release) | 640 | 48.8 | 67.2 | 424.5 | 10.9 | 2.7 | 46.5 | 109.1 |
Pretrained Checkpoints
| Model | size (pixels) |
mAPval 0.5:0.95 |
mAPval 0.5 |
Speed CPU b1 (ms) |
Speed V100 b1 (ms) |
Speed V100 b32 (ms) |
params (M) |
FLOPs @640 (B) |
|---|---|---|---|---|---|---|---|---|
| YOLOv5n | 640 | 28.4 | 46.0 | 45 | 6.3 | 0.6 | 1.9 | 4.5 |
| YOLOv5s | 640 | 37.2 | 56.0 | 98 | 6.4 | 0.9 | 7.2 | 16.5 |
| YOLOv5m | 640 | 45.2 | 63.9 | 224 | 8.2 | 1.7 | 21.2 | 49.0 |
| YOLOv5l | 640 | 48.8 | 67.2 | 430 | 10.1 | 2.7 | 46.5 | 109.1 |
| YOLOv5x | 640 | 50.7 | 68.9 | 766 | 12.1 | 4.8 | 86.7 | 205.7 |
| YOLOv5n6 | 1280 | 34.0 | 50.7 | 153 | 8.1 | 2.1 | 3.2 | 4.6 |
| YOLOv5s6 | 1280 | 44.5 | 63.0 | 385 | 8.2 | 3.6 | 16.8 | 12.6 |
| YOLOv5m6 | 1280 | 51.0 | 69.0 | 887 | 11.1 | 6.8 | 35.7 | 50.0 |
| YOLOv5l6 | 1280 | 53.6 | 71.6 | 1784 | 15.8 | 10.5 | 76.8 | 111.4 |
| YOLOv5x6 + TTA |
1280 1536 |
54.7 55.4 |
72.4 72.3 |
3136 - |
26.2 - |
19.4 - |
140.7 - |
209.8 - |
Table Notes (click to expand)
* All checkpoints are trained to 300 epochs with default settings. Nano models use [hyp.scratch-low.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-low.yaml) hyperparameters, all others use [hyp.scratch-high.yaml](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-high.yaml). * **mAPval** values are for single-model single-scale on [COCO val2017](http://cocodataset.org) dataset.Reproduce by `python val.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65` * **Speed** averaged over COCO val images using a [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/) instance. NMS times (~1 ms/img) not included.
Reproduce by `python val.py --data coco.yaml --img 640 --conf 0.25 --iou 0.45` * **TTA** [Test Time Augmentation](https://github.com/ultralytics/yolov5/issues/303) includes reflection and scale augmentations.
Reproduce by `python val.py --data coco.yaml --img 1536 --iou 0.7 --augment`
Changelog
Changes between previous release and this release: https://github.com/ultralytics/yolov5/compare/v5.0...v6.0 Changes since this release: https://github.com/ultralytics/yolov5/compare/v6.0...HEAD
