2022-12-09 09:27:36 +08:00
< div align = "center" >
< p >
< a align = "center" href = "https://ultralytics.com/yolov5" target = "_blank" >
2023-01-04 02:21:31 +08:00
< img width = "850" src = "https://raw.githubusercontent.com/ultralytics/assets/main/yolov5/v70/splash.png" > < / a >
2022-12-09 09:27:36 +08:00
< / p >
2023-02-06 19:11:32 +08:00
[英文 ](README.md )|[简体中文](README.zh-CN.md)< br >
2022-12-09 09:27:36 +08:00
2023-02-06 19:11:32 +08:00
< div >
2022-12-09 09:27:36 +08:00
< 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 >
< a href = "https://zenodo.org/badge/latestdoi/264818686" > < img src = "https://zenodo.org/badge/264818686.svg" alt = "YOLOv5 Citation" > < / a >
< 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 >
< br >
< 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 >
< / div >
< br >
2022-12-14 06:48:15 +08:00
YOLOv5 🚀 是世界上最受欢迎的视觉 AI， < a href = "https://ultralytics.com" > Ultralytics < / a > 对未来视觉 AI 方法的开源研究，结合在数千小时的研究和开发中积累的经验教训和最佳实践。
2022-12-09 09:27:36 +08:00
2022-12-14 06:48:15 +08:00
如果要申请企业许可证，请填写表格< a href = "https://ultralytics.com/license" > Ultralytics 许可< / a > .
2022-12-09 09:27:36 +08:00
2023-02-06 19:11:32 +08:00
< div align = "center" >
2022-12-09 09:27:36 +08:00
< a href = "https://github.com/ultralytics" style = "text-decoration:none;" >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-social-github.png" width = "2%" alt = "" / > < / a >
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "2%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://www.linkedin.com/company/ultralytics" style = "text-decoration:none;" >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-social-linkedin.png" width = "2%" alt = "" / > < / a >
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "2%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://twitter.com/ultralytics" style = "text-decoration:none;" >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-social-twitter.png" width = "2%" alt = "" / > < / a >
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "2%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://www.producthunt.com/@glenn_jocher" style = "text-decoration:none;" >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-social-producthunt.png" width = "2%" alt = "" / > < / a >
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "2%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://youtube.com/ultralytics" style = "text-decoration:none;" >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-social-youtube.png" width = "2%" alt = "" / > < / a >
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "2%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://www.facebook.com/ultralytics" style = "text-decoration:none;" >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-social-facebook.png" width = "2%" alt = "" / > < / a >
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "2%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://www.instagram.com/ultralytics/" style = "text-decoration:none;" >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-social-instagram.png" width = "2%" alt = "" / > < / a >
2022-12-09 09:27:36 +08:00
< / div >
< / div >
2022-12-14 06:48:15 +08:00
## <div align="center">实例分割模型 ⭐ 新</div>
2022-12-09 09:27:36 +08:00
< div align = "center" >
< a align = "center" href = "https://ultralytics.com/yolov5" target = "_blank" >
< img width = "800" src = "https://user-images.githubusercontent.com/61612323/204180385-84f3aca9-a5e9-43d8-a617-dda7ca12e54a.png" > < / a >
< / div >
2022-12-14 06:48:15 +08:00
我们新的 YOLOv5 [release v7.0 ](https://github.com/ultralytics/yolov5/releases/v7.0 ) 实例分割模型是世界上最快和最准确的模型，击败所有当前 [SOTA 基准 ](https://paperswithcode.com/sota/real-time-instance-segmentation-on-mscoco )。我们使它非常易于训练、验证和部署。更多细节请查看 [发行说明 ](https://github.com/ultralytics/yolov5/releases/v7.0 ) 或访问我们的 [YOLOv5 分割 Colab 笔记本 ](https://github.com/ultralytics/yolov5/blob/master/segment/tutorial.ipynb ) 以快速入门。
2022-12-09 09:27:36 +08:00
< details >
2022-12-14 06:48:15 +08:00
< summary > 实例分割模型列表< / summary >
2022-12-09 09:27:36 +08:00
< br >
2022-12-14 06:48:15 +08:00
我们使用 A100 GPU 在 COCO 上以 640 图像大小训练了 300 epochs 得到 YOLOv5 分割模型。我们将所有模型导出到 ONNX FP32 以进行 CPU 速度测试，并导出到 TensorRT FP16 以进行 GPU 速度测试。为了便于再现，我们在 Google [Colab Pro ](https://colab.research.google.com/signup ) 上进行了所有速度测试。
2022-12-09 09:27:36 +08:00
2023-02-06 19:11:32 +08:00
| 模型 | 尺寸< br > < sup > （像素） | mAP< sup > box< br > 50-95 | mAP< sup > mask< br > 50-95 | 训练时长< br > < sup > 300 epochs< br > A100 GPU（ ） < br > < sup > ONNX CPU< br > （ ） < br > < sup > TRT A100< br > （ ） < br > < sup > (M) | FLOPs< br > < sup > @640 (B) |
| ------------------------------------------------------------------------------------------ | --------------- | -------------------- | --------------------- | --------------------------------------- | ----------------------------- | ----------------------------- | --------------- | ---------------------- |
| [YOLOv5n-seg ](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5n-seg.pt ) | 640 | 27.6 | 23.4 | 80:17 | **62.7** | **1.2** | **2.0** | **7.1** |
| [YOLOv5s-seg ](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5s-seg.pt ) | 640 | 37.6 | 31.7 | 88:16 | 173.3 | 1.4 | 7.6 | 26.4 |
| [YOLOv5m-seg ](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5m-seg.pt ) | 640 | 45.0 | 37.1 | 108:36 | 427.0 | 2.2 | 22.0 | 70.8 |
| [YOLOv5l-seg ](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5l-seg.pt ) | 640 | 49.0 | 39.9 | 66:43 (2x) | 857.4 | 2.9 | 47.9 | 147.7 |
| [YOLOv5x-seg ](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5x-seg.pt ) | 640 | **50.7** | **41.4** | 62:56 (3x) | 1579.2 | 4.5 | 88.8 | 265.7 |
2022-12-09 09:27:36 +08:00
2023-02-06 19:11:32 +08:00
- 所有模型使用 SGD 优化器训练， 都使用 `lr0=0.01` 和 `weight_decay=5e-5` 参数， 图像大小为 640 。< br > 训练 log 可以查看 https://wandb.ai/glenn-jocher/YOLOv5_v70_official
- **准确性**结果都在 COCO 数据集上，使用单模型单尺度测试得到。< br > 复现命令 `python segment/val.py --data coco.yaml --weights yolov5s-seg.pt`
- **推理速度**是使用 100 张图像推理时间进行平均得到，测试环境使用 [Colab Pro ](https://colab.research.google.com/signup ) 上 A100 高 RAM 实例。结果仅表示推理速度（ < br > 复现命令 `python segment/val.py --data coco.yaml --weights yolov5s-seg.pt --batch 1`
- **模型转换**到 FP32 的 ONNX 和 FP16 的 TensorRT 脚本为 `export.py` .< br > 运行命令 `python export.py --weights yolov5s-seg.pt --include engine --device 0 --half`
2022-12-09 09:27:36 +08:00
< / details >
< details >
2022-12-14 06:48:15 +08:00
< summary > 分割模型使用示例 < a href = "https://colab.research.google.com/github/ultralytics/yolov5/blob/master/segment/tutorial.ipynb" > < img src = "https://colab.research.google.com/assets/colab-badge.svg" alt = "Open In Colab" > < / a > < / summary >
2022-12-09 09:27:36 +08:00
2022-12-14 06:48:15 +08:00
### 训练
2022-12-09 09:27:36 +08:00
2022-12-14 06:48:15 +08:00
YOLOv5分割训练支持自动下载 COCO128-seg 分割数据集，用户仅需在启动指令中包含 `--data coco128-seg.yaml` 参数。 若要手动下载，使用命令 `bash data/scripts/get_coco.sh --train --val --segments` ， `python train.py --data coco.yaml` 开启训练。
2022-12-09 09:27:36 +08:00
```bash
2022-12-14 06:48:15 +08:00
# 单 GPU
2022-12-09 09:27:36 +08:00
python segment/train.py --data coco128-seg.yaml --weights yolov5s-seg.pt --img 640
2022-12-14 06:48:15 +08:00
# 多 GPU，
2022-12-09 09:27:36 +08:00
python -m torch.distributed.run --nproc_per_node 4 --master_port 1 segment/train.py --data coco128-seg.yaml --weights yolov5s-seg.pt --img 640 --device 0,1,2,3
```
2022-12-14 06:48:15 +08:00
### 验证
2022-12-09 09:27:36 +08:00
在 COCO 数据集上验证 YOLOv5s-seg mask mAP：
```bash
2022-12-14 06:48:15 +08:00
bash data/scripts/get_coco.sh --val --segments # 下载 COCO val segments 数据集 (780MB, 5000 images)
python segment/val.py --weights yolov5s-seg.pt --data coco.yaml --img 640 # 验证
2022-12-09 09:27:36 +08:00
```
### 预测
使用预训练的 YOLOv5m-seg.pt 来预测 bus.jpg：
```bash
python segment/predict.py --weights yolov5m-seg.pt --data data/images/bus.jpg
```
```python
2023-02-06 19:11:32 +08:00
model = torch.hub.load(
"ultralytics/yolov5", "custom", "yolov5m-seg.pt"
) # 从load from PyTorch Hub 加载模型 (WARNING: 推理暂未支持)
2022-12-09 09:27:36 +08:00
```
|  |  |
| ---------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------- |
2022-12-14 06:48:15 +08:00
### 模型导出
2022-12-09 09:27:36 +08:00
将 YOLOv5s-seg 模型导出到 ONNX 和 TensorRT：
```bash
python export.py --weights yolov5s-seg.pt --include onnx engine --img 640 --device 0
```
< / details >
## <div align="center">文档</div>
2022-12-14 06:48:15 +08:00
有关训练、测试和部署的完整文档见[YOLOv5 文档](https://docs.ultralytics.com)。请参阅下面的快速入门示例。
2022-12-09 09:27:36 +08:00
< details open >
2022-12-14 06:48:15 +08:00
< summary > 安装< / summary >
2022-12-09 09:27:36 +08:00
2022-12-14 06:48:15 +08:00
克隆 repo， **Python>=3.7.0** ](https://www.python.org/ ) 环境中安装 [requirements.txt ](https://github.com/ultralytics/yolov5/blob/master/requirements.txt ) ，且要求 [**PyTorch>=1.7** ](https://pytorch.org/get-started/locally/ ) 。
2022-12-09 09:27:36 +08:00
```bash
git clone https://github.com/ultralytics/yolov5 # clone
cd yolov5
pip install -r requirements.txt # install
```
< / details >
< details >
2022-12-14 06:48:15 +08:00
< summary > 推理< / summary >
2022-12-09 09:27:36 +08:00
2022-12-14 06:48:15 +08:00
使用 YOLOv5 [PyTorch Hub ](https://github.com/ultralytics/yolov5/issues/36 ) 推理。最新 [模型 ](https://github.com/ultralytics/yolov5/tree/master/models ) 将自动的从
YOLOv5 [release ](https://github.com/ultralytics/yolov5/releases ) 中下载。
2022-12-09 09:27:36 +08:00
```python
import torch
# Model
2023-02-06 19:11:32 +08:00
model = torch.hub.load("ultralytics/yolov5", "yolov5s") # or yolov5n - yolov5x6, custom
2022-12-09 09:27:36 +08:00
# Images
2023-02-06 19:11:32 +08:00
img = "https://ultralytics.com/images/zidane.jpg" # or file, Path, PIL, OpenCV, numpy, list
2022-12-09 09:27:36 +08:00
# Inference
results = model(img)
# Results
results.print() # or .show(), .save(), .crop(), .pandas(), etc.
```
< / details >
< details >
2022-12-14 06:48:15 +08:00
< summary > 使用 detect.py 推理< / summary >
2022-12-09 09:27:36 +08:00
2022-12-14 06:48:15 +08:00
`detect.py` 在各种来源上运行推理， [模型 ](https://github.com/ultralytics/yolov5/tree/master/models ) 自动从
最新的YOLOv5 [release ](https://github.com/ultralytics/yolov5/releases ) 中下载，并将结果保存到 `runs/detect` 。
2022-12-09 09:27:36 +08:00
```bash
python detect.py --weights yolov5s.pt --source 0 # webcam
img.jpg # image
vid.mp4 # video
screen # screenshot
path/ # directory
list.txt # list of images
list.streams # list of streams
'path/*.jpg' # glob
'https://youtu.be/Zgi9g1ksQHc' # YouTube
'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
```
< / details >
< details >
2022-12-14 06:48:15 +08:00
< summary > 训练< / summary >
2022-12-09 09:27:36 +08:00
2022-12-14 06:48:15 +08:00
下面的命令重现 YOLOv5 在 [COCO ](https://github.com/ultralytics/yolov5/blob/master/data/scripts/get_coco.sh ) 数据集上的结果。
最新的 [模型 ](https://github.com/ultralytics/yolov5/tree/master/models ) 和 [数据集 ](https://github.com/ultralytics/yolov5/tree/master/data )
将自动的从 YOLOv5 [release ](https://github.com/ultralytics/yolov5/releases ) 中下载。
YOLOv5n/s/m/l/x 在 V100 GPU 的训练时间为 1/2/4/6/8 天（ [多GPU ](https://github.com/ultralytics/yolov5/issues/475 ) 训练速度更快）。
尽可能使用更大的 `--batch-size` ，或通过 `--batch-size -1` 实现
YOLOv5 [自动批处理 ](https://github.com/ultralytics/yolov5/pull/5092 ) 。下方显示的 batchsize 适用于 V100-16GB。
2022-12-09 09:27:36 +08:00
```bash
python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5n.yaml --batch-size 128
yolov5s 64
yolov5m 40
yolov5l 24
yolov5x 16
```
< img width = "800" src = "https://user-images.githubusercontent.com/26833433/90222759-949d8800-ddc1-11ea-9fa1-1c97eed2b963.png" >
< / details >
< details open >
2022-12-14 06:48:15 +08:00
< summary > 教程< / summary >
2022-12-09 09:27:36 +08:00
2023-02-06 19:11:32 +08:00
- [训练自定义数据 ](https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data )🚀 推荐
- [获得最佳训练结果的技巧 ](https://github.com/ultralytics/yolov5/wiki/Tips-for-Best-Training-Results )☘️ 推荐
- [多 GPU 训练 ](https://github.com/ultralytics/yolov5/issues/475 )
- [PyTorch Hub ](https://github.com/ultralytics/yolov5/issues/36 )🌟 新
- [TFLite、ONNX、CoreML、TensorRT 导出 ](https://github.com/ultralytics/yolov5/issues/251 )🚀
- [NVIDIA Jetson Nano 部署 ](https://github.com/ultralytics/yolov5/issues/9627 )🌟 新
- [测试时数据增强 (TTA) ](https://github.com/ultralytics/yolov5/issues/303 )
- [模型集成 ](https://github.com/ultralytics/yolov5/issues/318 )
- [模型修剪/稀疏度 ](https://github.com/ultralytics/yolov5/issues/304 )
- [超参数进化 ](https://github.com/ultralytics/yolov5/issues/607 )
- [使用冻结层进行迁移学习 ](https://github.com/ultralytics/yolov5/issues/1314 )
- [架构总结 ](https://github.com/ultralytics/yolov5/issues/6998 )🌟 新
- [用于数据集、标签和主动学习的 Roboflow ](https://github.com/ultralytics/yolov5/issues/4975 )🌟 新
- [ClearML 记录 ](https://github.com/ultralytics/yolov5/tree/master/utils/loggers/clearml )🌟 新
- [Deci 平台 ](https://github.com/ultralytics/yolov5/wiki/Deci-Platform )🌟 新
- [Comet Logging ](https://github.com/ultralytics/yolov5/tree/master/utils/loggers/comet )🌟 新
2022-12-09 09:27:36 +08:00
< / details >
2022-12-14 06:48:15 +08:00
## <div align="center">模块集成</div>
2022-12-09 09:27:36 +08:00
< br >
< a align = "center" href = "https://bit.ly/ultralytics_hub" target = "_blank" >
2023-01-04 02:21:31 +08:00
< img width = "100%" src = "https://github.com/ultralytics/assets/raw/main/im/integrations-loop.png" > < / a >
2022-12-09 09:27:36 +08:00
< br >
< br >
< div align = "center" >
< a href = "https://roboflow.com/?ref=ultralytics" >
< img src = "https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-roboflow.png" width = "10%" / > < / a >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "15%" height = "0" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://cutt.ly/yolov5-readme-clearml" >
< img src = "https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-clearml.png" width = "10%" / > < / a >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "15%" height = "0" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://bit.ly/yolov5-readme-comet" >
< img src = "https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-comet.png" width = "10%" / > < / a >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "15%" height = "0" alt = "" / >
2023-01-10 22:05:41 +08:00
< a href = "https://bit.ly/yolov5-neuralmagic" >
2023-01-10 16:40:17 +08:00
< img src = "https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-neuralmagic.png" width = "10%" / > < / a >
2022-12-09 09:27:36 +08:00
< / div >
2023-02-06 19:11:32 +08:00
| Roboflow | ClearML ⭐ 新 | Comet ⭐ 新 | Neural Magic ⭐ 新 |
| :--------------------------------------------------------------------------------: | :-------------------------------------------------------------------------: | :-------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------: |
2023-01-10 16:40:17 +08:00
| 将您的自定义数据集进行标注并直接导出到 YOLOv5 以进行训练 [Roboflow ](https://roboflow.com/?ref=ultralytics ) | 自动跟踪、可视化甚至远程训练 YOLOv5 [ClearML ](https://cutt.ly/yolov5-readme-clearml )（开源！） | 永远免费，[Comet](https://bit.ly/yolov5-readme-comet)可让您保存 YOLOv5 模型、恢复训练以及交互式可视化和调试预测 | 使用 [Neural Magic DeepSparse ](https://bit.ly/yolov5-neuralmagic )，运行 YOLOv5 推理的速度最高可提高6倍 |
2022-12-09 09:27:36 +08:00
2022-12-14 06:48:15 +08:00
## <div align="center">Ultralytics HUB</div>
2022-12-09 09:27:36 +08:00
2022-12-14 06:48:15 +08:00
[Ultralytics HUB ](https://bit.ly/ultralytics_hub ) 是我们的⭐**新的**用于可视化数据集、训练 YOLOv5 🚀 模型并以无缝体验部署到现实世界的无代码解决方案。现在开始 ** 免费** 使用他！
2022-12-09 09:27:36 +08:00
< a align = "center" href = "https://bit.ly/ultralytics_hub" target = "_blank" >
2023-01-04 02:21:31 +08:00
< img width = "100%" src = "https://github.com/ultralytics/assets/raw/main/im/ultralytics-hub.png" > < / a >
2022-12-09 09:27:36 +08:00
## <div align="center">为什么选择 YOLOv5</div>
2022-12-14 06:48:15 +08:00
YOLOv5 超级容易上手，简单易学。我们优先考虑现实世界的结果。
2022-12-09 09:27:36 +08:00
< p align = "left" > < img width = "800" src = "https://user-images.githubusercontent.com/26833433/155040763-93c22a27-347c-4e3c-847a-8094621d3f4e.png" > < / p >
< details >
2022-12-14 06:48:15 +08:00
< summary > YOLOv5-P5 640 图< / summary >
2022-12-09 09:27:36 +08:00
< p align = "left" > < img width = "800" src = "https://user-images.githubusercontent.com/26833433/155040757-ce0934a3-06a6-43dc-a979-2edbbd69ea0e.png" > < / p >
< / details >
< details >
2022-12-14 06:48:15 +08:00
< summary > 图表笔记< / summary >
2022-12-09 09:27:36 +08:00
2023-02-06 19:11:32 +08:00
- **COCO AP val** 表示 mAP@0.5:0.95 指标，在 [COCO val2017 ](http://cocodataset.org ) 数据集的 5000 张图像上测得， 图像包含 256 到 1536 各种推理大小。
- **显卡推理速度** 为在 [COCO val2017 ](http://cocodataset.org ) 数据集上的平均推理时间，使用 [AWS p3.2xlarge ](https://aws.amazon.com/ec2/instance-types/p3/ ) V100实例，
- **EfficientDet** 数据来自 [google/automl ](https://github.com/google/automl ) ，
- **复现命令** 为 `python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n6.pt yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt`
2022-12-09 09:27:36 +08:00
< / details >
2022-12-14 06:48:15 +08:00
### 预训练模型
2023-02-06 19:11:32 +08:00
| 模型 | 尺寸< br > < sup > （像素） | mAP< sup > val< br > 50-95 | mAP< sup > val< br > 50 | 推理速度< br > < sup > CPU b1< br > （ ） < br > < sup > V100 b1< br > （ ） < br > < sup > V100 b32< br > （ ） < br > < sup > (M) | FLOPs< br > < sup > @640 (B) |
| ---------------------------------------------------------------------------------------------- | --------------- | -------------------- | ----------------- | --------------------------- | ---------------------------- | --------------------------- | --------------- | ---------------------- |
| [YOLOv5n ](https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5n.pt ) | 640 | 28.0 | 45.7 | **45** | **6.3** | **0.6** | **1.9** | **4.5** |
| [YOLOv5s ](https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5s.pt ) | 640 | 37.4 | 56.8 | 98 | 6.4 | 0.9 | 7.2 | 16.5 |
| [YOLOv5m ](https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5m.pt ) | 640 | 45.4 | 64.1 | 224 | 8.2 | 1.7 | 21.2 | 49.0 |
| [YOLOv5l ](https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5l.pt ) | 640 | 49.0 | 67.3 | 430 | 10.1 | 2.7 | 46.5 | 109.1 |
| [YOLOv5x ](https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5x.pt ) | 640 | 50.7 | 68.9 | 766 | 12.1 | 4.8 | 86.7 | 205.7 |
| | | | | | | | | |
| [YOLOv5n6 ](https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5n6.pt ) | 1280 | 36.0 | 54.4 | 153 | 8.1 | 2.1 | 3.2 | 4.6 |
| [YOLOv5s6 ](https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5s6.pt ) | 1280 | 44.8 | 63.7 | 385 | 8.2 | 3.6 | 12.6 | 16.8 |
| [YOLOv5m6 ](https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5m6.pt ) | 1280 | 51.3 | 69.3 | 887 | 11.1 | 6.8 | 35.7 | 50.0 |
| [YOLOv5l6 ](https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5l6.pt ) | 1280 | 53.7 | 71.3 | 1784 | 15.8 | 10.5 | 76.8 | 111.4 |
| [YOLOv5x6 ](https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5x6.pt )< br > +[TTA] | 1280< br > 1536 | 55.0< br > **55.8** | 72.7< br > **72.7** | 3136< br > - | 26.2< br > - | 19.4< br > - | 140.7< br > - | 209.8< br > - |
2022-12-09 09:27:36 +08:00
< details >
2022-12-14 06:48:15 +08:00
< summary > 笔记< / summary >
2022-12-09 09:27:36 +08:00
2023-02-06 19:11:32 +08:00
- 所有模型都使用默认配置，训练 300 epochs。n和s模型使用 [hyp.scratch-low.yaml ](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-low.yaml ) ，其他模型都使用 [hyp.scratch-high.yaml ](https://github.com/ultralytics/yolov5/blob/master/data/hyps/hyp.scratch-high.yaml ) 。
- \*\*mAP< sup > val</ sup > \*\*在单模型单尺度上计算，数据集使用 [COCO val2017 ](http://cocodataset.org ) 。< br > 复现命令 `python val.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65`
- **推理速度**在 COCO val 图像总体时间上进行平均得到，测试环境使用[AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/)实例。 NMS 时间 (大约 1 ms/img) 不包括在内。< br > 复现命令 `python val.py --data coco.yaml --img 640 --task speed --batch 1`
- **TTA** [测试时数据增强 ](https://github.com/ultralytics/yolov5/issues/303 ) 包括反射和尺度变换。< br > 复现命令 `python val.py --data coco.yaml --img 1536 --iou 0.7 --augment`
2022-12-09 09:27:36 +08:00
< / details >
2022-12-14 06:48:15 +08:00
## <div align="center">分类网络 ⭐ 新</div>
2022-12-09 09:27:36 +08:00
2022-12-14 06:48:15 +08:00
YOLOv5 [release v6.2 ](https://github.com/ultralytics/yolov5/releases ) 带来对分类模型训练、验证和部署的支持！详情请查看 [发行说明 ](https://github.com/ultralytics/yolov5/releases/v6.2 ) 或访问我们的 [YOLOv5 分类 Colab 笔记本 ](https://github.com/ultralytics/yolov5/blob/master/classify/tutorial.ipynb ) 以快速入门。
2022-12-09 09:27:36 +08:00
< details >
2022-12-14 06:48:15 +08:00
< summary > 分类网络模型< / summary >
2022-12-09 09:27:36 +08:00
< br >
2022-12-14 06:48:15 +08:00
我们使用 4xA100 实例在 ImageNet 上训练了 90 个 epochs 得到 YOLOv5-cls 分类模型，我们训练了 ResNet 和 EfficientNet 模型以及相同的默认训练设置以进行比较。我们将所有模型导出到 ONNX FP32 以进行 CPU 速度测试，并导出到 TensorRT FP16 以进行 GPU 速度测试。为了便于重现，我们在 Google 上进行了所有速度测试 [Colab Pro ](https://colab.research.google.com/signup ) 。
2023-02-06 19:11:32 +08:00
| 模型 | 尺寸< br > < sup > （像素） | acc< br > < sup > top1 | acc< br > < sup > top5 | 训练时长< br > < sup > 90 epochs< br > 4xA100（ ） < br > < sup > ONNX CPU< br > （ ） < br > < sup > TensorRT V100< br > （ ） < br > < sup > (M) | FLOPs< br > < sup > @640 (B) |
| -------------------------------------------------------------------------------------------------- | --------------- | ---------------- | ---------------- | ------------------------------------ | ----------------------------- | ---------------------------------- | -------------- | ---------------------- |
| [YOLOv5n-cls ](https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5n-cls.pt ) | 224 | 64.6 | 85.4 | 7:59 | **3.3** | **0.5** | **2.5** | **0.5** |
| [YOLOv5s-cls ](https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5s-cls.pt ) | 224 | 71.5 | 90.2 | 8:09 | 6.6 | 0.6 | 5.4 | 1.4 |
| [YOLOv5m-cls ](https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5m-cls.pt ) | 224 | 75.9 | 92.9 | 10:06 | 15.5 | 0.9 | 12.9 | 3.9 |
| [YOLOv5l-cls ](https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5l-cls.pt ) | 224 | 78.0 | 94.0 | 11:56 | 26.9 | 1.4 | 26.5 | 8.5 |
| [YOLOv5x-cls ](https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5x-cls.pt ) | 224 | **79.0** | **94.4** | 15:04 | 54.3 | 1.8 | 48.1 | 15.9 |
| | | | | | | | | |
| [ResNet18 ](https://github.com/ultralytics/yolov5/releases/download/v6.2/resnet18.pt ) | 224 | 70.3 | 89.5 | **6:47** | 11.2 | 0.5 | 11.7 | 3.7 |
| [Resnetzch ](https://github.com/ultralytics/yolov5/releases/download/v6.2/resnet34.pt ) | 224 | 73.9 | 91.8 | 8:33 | 20.6 | 0.9 | 21.8 | 7.4 |
| [ResNet50 ](https://github.com/ultralytics/yolov5/releases/download/v6.2/resnet50.pt ) | 224 | 76.8 | 93.4 | 11:10 | 23.4 | 1.0 | 25.6 | 8.5 |
| [ResNet101 ](https://github.com/ultralytics/yolov5/releases/download/v6.2/resnet101.pt ) | 224 | 78.5 | 94.3 | 17:10 | 42.1 | 1.9 | 44.5 | 15.9 |
| | | | | | | | | |
| [EfficientNet_b0 ](https://github.com/ultralytics/yolov5/releases/download/v6.2/efficientnet_b0.pt ) | 224 | 75.1 | 92.4 | 13:03 | 12.5 | 1.3 | 5.3 | 1.0 |
| [EfficientNet_b1 ](https://github.com/ultralytics/yolov5/releases/download/v6.2/efficientnet_b1.pt ) | 224 | 76.4 | 93.2 | 17:04 | 14.9 | 1.6 | 7.8 | 1.5 |
| [EfficientNet_b2 ](https://github.com/ultralytics/yolov5/releases/download/v6.2/efficientnet_b2.pt ) | 224 | 76.6 | 93.4 | 17:10 | 15.9 | 1.6 | 9.1 | 1.7 |
| [EfficientNet_b3 ](https://github.com/ultralytics/yolov5/releases/download/v6.2/efficientnet_b3.pt ) | 224 | 77.7 | 94.0 | 19:19 | 18.9 | 1.9 | 12.2 | 2.4 |
2022-12-09 09:27:36 +08:00
< details >
2022-12-14 06:48:15 +08:00
< summary > Table Notes (点击以展开)< / summary >
2022-12-09 09:27:36 +08:00
2023-02-06 19:11:32 +08:00
- 所有模型都使用 SGD 优化器训练 90 个 epochs， `lr0=0.001` 和 `weight_decay=5e-5` 参数， 图像大小为 224 ，且都使用默认设置。< br > 训练 log 可以查看 https://wandb.ai/glenn-jocher/YOLOv5-Classifier-v6-2
- **准确性**都在单模型单尺度上计算，数据集使用 [ImageNet-1k ](https://www.image-net.org/index.php ) 。< br > 复现命令 `python classify/val.py --data ../datasets/imagenet --img 224`
- **推理速度**是使用 100 个推理图像进行平均得到，测试环境使用谷歌 [Colab Pro ](https://colab.research.google.com/signup ) V100 高 RAM 实例。< br > 复现命令 `python classify/val.py --data ../datasets/imagenet --img 224 --batch 1`
- **模型导出**到 FP32 的 ONNX 和 FP16 的 TensorRT 使用 `export.py` 。< br > 复现命令 `python export.py --weights yolov5s-cls.pt --include engine onnx --imgsz 224`
< / details >
< / details >
2022-12-09 09:27:36 +08:00
< details >
2022-12-14 06:48:15 +08:00
< summary > 分类训练示例 < a href = "https://colab.research.google.com/github/ultralytics/yolov5/blob/master/classify/tutorial.ipynb" > < img src = "https://colab.research.google.com/assets/colab-badge.svg" alt = "Open In Colab" > < / a > < / summary >
2022-12-09 09:27:36 +08:00
2022-12-14 06:48:15 +08:00
### 训练
2022-12-09 09:27:36 +08:00
2022-12-14 06:48:15 +08:00
YOLOv5 分类训练支持自动下载 MNIST、Fashion-MNIST、CIFAR10、CIFAR100、Imagenette、Imagewoof 和 ImageNet 数据集，命令中使用 `--data` 即可。 MNIST 示例 `--data mnist` 。
2022-12-09 09:27:36 +08:00
```bash
2022-12-14 06:48:15 +08:00
# 单 GPU
2022-12-09 09:27:36 +08:00
python classify/train.py --model yolov5s-cls.pt --data cifar100 --epochs 5 --img 224 --batch 128
2022-12-14 06:48:15 +08:00
# 多 GPU，
2022-12-09 09:27:36 +08:00
python -m torch.distributed.run --nproc_per_node 4 --master_port 1 classify/train.py --model yolov5s-cls.pt --data imagenet --epochs 5 --img 224 --device 0,1,2,3
```
2022-12-14 06:48:15 +08:00
### 验证
2022-12-09 09:27:36 +08:00
在 ImageNet-1k 数据集上验证 YOLOv5m-cls 的准确性：
```bash
bash data/scripts/get_imagenet.sh --val # download ImageNet val split (6.3G, 50000 images)
python classify/val.py --weights yolov5m-cls.pt --data ../datasets/imagenet --img 224 # validate
```
### 预测
使用预训练的 YOLOv5s-cls.pt 来预测 bus.jpg：
```bash
python classify/predict.py --weights yolov5s-cls.pt --data data/images/bus.jpg
```
```python
2023-02-06 19:11:32 +08:00
model = torch.hub.load(
"ultralytics/yolov5", "custom", "yolov5s-cls.pt"
) # load from PyTorch Hub
2022-12-09 09:27:36 +08:00
```
2022-12-14 06:48:15 +08:00
### 模型导出
2022-12-09 09:27:36 +08:00
将一组经过训练的 YOLOv5s-cls、ResNet 和 EfficientNet 模型导出到 ONNX 和 TensorRT：
```bash
python export.py --weights yolov5s-cls.pt resnet50.pt efficientnet_b0.pt --include onnx engine --img 224
```
< / details >
## <div align="center">环境</div>
2022-12-14 06:48:15 +08:00
使用下面我们经过验证的环境，在几秒钟内开始使用 YOLOv5 。单击下面的图标了解详细信息。
2022-12-09 09:27:36 +08:00
< div align = "center" >
< a href = "https://bit.ly/yolov5-paperspace-notebook" >
< img src = "https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-gradient.png" width = "10%" / > < / a >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "5%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb" >
< img src = "https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-colab-small.png" width = "10%" / > < / a >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "5%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://www.kaggle.com/ultralytics/yolov5" >
< img src = "https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-kaggle-small.png" width = "10%" / > < / a >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "5%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://hub.docker.com/r/ultralytics/yolov5" >
< img src = "https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-docker-small.png" width = "10%" / > < / a >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "5%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart" >
< img src = "https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-aws-small.png" width = "10%" / > < / a >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "5%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart" >
< img src = "https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-gcp-small.png" width = "10%" / > < / a >
< / div >
2022-12-14 06:48:15 +08:00
## <div align="center">APP</div>
2022-12-09 09:47:14 +08:00
2022-12-14 06:48:15 +08:00
通过下载 [Ultralytics APP ](https://ultralytics.com/app_install ) ，以在您的 iOS 或 Android 设备上运行 YOLOv5 模型!
2022-12-09 09:47:14 +08:00
< a align = "center" href = "https://ultralytics.com/app_install" target = "_blank" >
< img width = "100%" alt = "Ultralytics mobile app" src = "https://user-images.githubusercontent.com/26833433/202829285-39367043-292a-41eb-bb76-c3e74f38e38e.png" >
2022-12-09 09:27:36 +08:00
## <div align="center">贡献</div>
2022-12-14 06:48:15 +08:00
我们喜欢您的意见或建议！我们希望尽可能简单和透明地为 YOLOv5 做出贡献。请看我们的 [投稿指南 ](CONTRIBUTING.md )，并填写 [YOLOv5调查 ](https://ultralytics.com/survey?utm_source=github&utm_medium=social&utm_campaign=Survey ) 向我们发送您的体验反馈。感谢我们所有的贡献者！
2022-12-09 09:27:36 +08:00
<!-- SVG image from https://opencollective.com/ultralytics/contributors.svg?width=990 -->
< a href = "https://github.com/ultralytics/yolov5/graphs/contributors" > < img src = "https://github.com/ultralytics/yolov5/releases/download/v1.0/image-contributors-1280.png" / > < / a >
2022-12-14 06:48:15 +08:00
## <div align="center">License</div>
2022-12-09 09:27:36 +08:00
2022-12-14 06:48:15 +08:00
YOLOv5 在两种不同的 License 下可用：
2022-12-09 09:27:36 +08:00
2023-02-06 19:11:32 +08:00
- **GPL-3.0 License**： License ](https://github.com/ultralytics/yolov5/blob/master/LICENSE ) 文件的详细信息。
- **企业License**：在没有 GPL-3.0 开源要求的情况下为商业产品开发提供更大的灵活性。典型用例是将 Ultralytics 软件和 AI 模型嵌入到商业产品和应用程序中。在以下位置申请企业许可证 [Ultralytics 许可 ](https://ultralytics.com/license ) 。
2022-12-09 09:27:36 +08:00
2022-12-14 06:48:15 +08:00
## <div align="center">联系我们</div>
2022-12-09 09:27:36 +08:00
2022-12-14 06:48:15 +08:00
若发现 YOLOv5 的 bug 或有功能需求，请访问 [GitHub 问题 ](https://github.com/ultralytics/yolov5/issues ) 。如需专业支持，请 [联系我们 ](https://ultralytics.com/contact ) 。
2022-12-09 09:27:36 +08:00
< br >
< div align = "center" >
< a href = "https://github.com/ultralytics" style = "text-decoration:none;" >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-social-github.png" width = "3%" alt = "" / > < / a >
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "3%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://www.linkedin.com/company/ultralytics" style = "text-decoration:none;" >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-social-linkedin.png" width = "3%" alt = "" / > < / a >
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "3%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://twitter.com/ultralytics" style = "text-decoration:none;" >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-social-twitter.png" width = "3%" alt = "" / > < / a >
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "3%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://www.producthunt.com/@glenn_jocher" style = "text-decoration:none;" >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-social-producthunt.png" width = "3%" alt = "" / > < / a >
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "3%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://youtube.com/ultralytics" style = "text-decoration:none;" >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-social-youtube.png" width = "3%" alt = "" / > < / a >
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "3%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://www.facebook.com/ultralytics" style = "text-decoration:none;" >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-social-facebook.png" width = "3%" alt = "" / > < / a >
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width = "3%" alt = "" / >
2022-12-09 09:27:36 +08:00
< a href = "https://www.instagram.com/ultralytics/" style = "text-decoration:none;" >
2023-01-04 02:21:31 +08:00
< img src = "https://github.com/ultralytics/assets/raw/main/social/logo-social-instagram.png" width = "3%" alt = "" / > < / a >
2022-12-09 09:27:36 +08:00
< / div >
[tta]: https://github.com/ultralytics/yolov5/issues/303
