命令行界面
Ultralytics 命令行界面 (CLI) 提供了一种简单直接的方式,让你无需编写 Python 代码即可使用 Ultralytics YOLO 模型。CLI 支持通过 yolo 命令直接在终端中运行所有任务和模式。
观看: 精通 Ultralytics YOLO:CLI
Ultralytics yolo 命令使用以下语法:
yolo TASK MODE ARGS其中:
TASK(可选)是 [detect, segment, semantic, depth, classify, pose, obb] 中的一项MODE(必需)是 [train, val, predict, export, track, benchmark] 中的一项ARGS(可选)可以是任意数量的自定义arg=value键值对,例如imgsz=320,用于覆盖默认值。
请查看完整的配置指南或使用 yolo cfg 查看所有 ARGS。
其中:
TASK(可选)是[detect, segment, semantic, depth, classify, pose, obb]中的一项。如果未明确指定,YOLO 会尝试根据模型类型推断TASK。MODE(必需)是[train, val, predict, export, track, benchmark]中的一项ARGS(可选)可以是任意数量的自定义arg=value键值对,例如imgsz=320,用于覆盖默认值。有关所有可用ARGS的完整列表,请参阅配置页面和default.yaml。
参数必须以 arg=val 键值对的形式传入,键和值之间用等号 = 分隔,键值对之间用空格分隔。不要使用 -- 参数前缀,也不要在参数之间使用逗号 ,。
yolo predict model=yolo26n.pt imgsz=640 conf=0.25✅yolo predict model yolo26n.pt imgsz 640 conf 0.25❌yolo predict --model yolo26n.pt --imgsz 640 --conf 0.25❌
训练#
训练 YOLO 时,使用 COCO8 数据集、图像尺寸 640,并运行 100 个周期。
开始在 COCO8 上训练 YOLO26n 100 个 epoch,图像尺寸设为 640:
yolo detect train data=coco8.yaml model=yolo26n.pt epochs=100 imgsz=640验证#
在 COCO8 数据集上验证训练后模型的准确率。对于自定义模型,如果省略 data,则会沿用训练时的 data;对于官方权重,则回退到任务默认的 coco8.yaml。
验证官方 YOLO26n 模型:
yolo detect val model=yolo26n.pt data=coco8.yaml预测#
使用训练好的模型对图像进行预测。
使用官方 YOLO26n 模型进行预测:
yolo detect predict model=yolo26n.pt source='https://ultralytics.com/images/bus.jpg'导出#
将模型导出为其他格式,例如 ONNX 或 CoreML。
将官方 YOLO26n 模型导出为 ONNX 格式:
yolo export model=yolo26n.pt format=onnx下表列出了可用的 Ultralytics 导出格式。你可以使用 format 参数导出为任意格式,例如 format='onnx' 或 format='engine'。
| 格式 | format 参数 | 模型 | 元数据 | 参数 |
|---|---|---|---|---|
| PyTorch | - | yolo26n.pt | ✅ | - |
| TorchScript | torchscript | yolo26n.torchscript | ✅ | imgsz, quantize, dynamic, nms, batch, device |
| ONNX | onnx | yolo26n.onnx | ✅ | imgsz, quantize, dynamic, simplify, opset, nms, batch, data, fraction, device |
| OpenVINO | openvino | yolo26n_openvino_model/ | ✅ | imgsz, quantize, dynamic, nms, batch, data, fraction, device |
| TensorRT | engine | yolo26n.engine | ✅ | imgsz, quantize, dynamic, simplify, opset, workspace, nms, batch, data, fraction, device |
| CoreML | coreml | yolo26n.mlpackage | ✅ | imgsz, dynamic, quantize, nms, batch, device |
| Apple Core AI | coreai | yolo26n.aimodel | ✅ | imgsz, batch, quantize |
| TF SavedModel | saved_model | yolo26n_saved_model/ | ✅ | imgsz, quantize, opset, nms, batch, data, fraction, device |
| TF GraphDef | pb | yolo26n.pb | ❌ | imgsz, opset, batch, device |
| TF Edge TPU | edgetpu | yolo26n_edgetpu.tflite | ✅ | imgsz, quantize, opset, data, fraction, device |
| LiteRT | litert | yolo26n.tflite | ✅ | imgsz, quantize, batch, data, fraction, device |
| PaddlePaddle | paddle | yolo26n_paddle_model/ | ✅ | imgsz, batch, device |
| MNN | mnn | yolo26n.mnn | ✅ | imgsz, batch, dynamic, quantize, simplify, opset, nms, device |
| NCNN | ncnn | yolo26n_ncnn_model/ | ✅ | imgsz, quantize, device |
| IMX500 | imx | yolo11n_imx_model/ | ✅ | imgsz, quantize, data, fraction, nms, device |
| RKNN | rknn | yolo26n_rknn_model/ | ✅ | imgsz, batch, name, quantize, simplify, opset, data, fraction, device |
| ExecuTorch | executorch | yolo26n_executorch_model/ | ✅ | imgsz, quantize, batch, data, fraction, device |
| Axelera | axelera | yolo26n_axelera_model/ | ✅ | imgsz, batch, quantize, data, fraction, device |
| DEEPX | deepx | yolo26n_deepx_model/ | ✅ | imgsz, quantize, simplify, opset, data, optimize, device |
| Qualcomm QNN | qnn | yolo26n_qnn.onnx | ✅ | imgsz, batch, name, quantize, simplify, opset, data, fraction, device |
| Hailo | hailo | yolo26n_hailo_model/ | ✅ | imgsz, name, quantize, data, fraction, simplify, conf, iou, device |
| Huawei Ascend | ascend | yolo26n_ascend_model/ | ✅ | imgsz, batch, name, quantize, opset, simplify, nms, device |
| AMD Xilinx | xilinx | yolo26n_xilinx_model/ | ✅ | imgsz, name, quantize, data, fraction, opset, simplify, device |
| NXP | nxp | yolo26n_nxp.tflite | ✅ | imgsz, quantize, data, fraction, device |
| ST Edge AI | stedgeai | yolo26n_stedgeai.onnx | ✅ | imgsz, quantize, data, fraction, opset, simplify, device |
nms=None 默认输出原始结果,以便进行外部 NMS(YOLO26 在 Axelera 上保留其无 NMS 检测头)。设置 nms=False 以选择可用的无 NMS 检测头;不支持的格式会回退到其原生输出路径。上方的 nms 条目指出可通过 nms=True 嵌入 NMS 的格式。
请在 导出 页面查看完整的 export 详情。
覆盖默认参数#
通过在 CLI 中以 arg=value 键值对的形式传入参数,即可覆盖默认参数。
以 0.01 的学习率训练检测模型 10 个周期:
yolo detect train data=coco8.yaml model=yolo26n.pt epochs=10 optimizer=SGD lr0=0.01覆盖默认配置文件#
通过 cfg 参数传入新文件(例如 cfg=custom.yaml),即可完全覆盖 default.yaml 配置文件。
首先,在当前工作目录中使用 yolo copy-cfg 命令创建 default.yaml 的副本,该命令会生成 default_copy.yaml 文件。
然后,你可以将此文件作为 cfg=default_copy.yaml 传入,并附加其他参数,例如本例中的 imgsz=320:
yolo copy-cfg
yolo cfg=default_copy.yaml imgsz=320解决方案命令#
Ultralytics 通过 CLI 提供可直接使用的解决方案,适用于常见的计算机视觉应用。yolo solutions 命令提供目标计数、裁剪、模糊处理、锻炼监测、热力图、实例分割、VisionEye、速度估算、队列管理、分析、Streamlit 推理、基于区域的跟踪、区域计数、安全警报和停车管理;完整目录请参阅解决方案页面。运行 yolo solutions help 可列出所有支持的解决方案及其参数。
统计视频或实时流中的对象:
yolo solutions count show=True
yolo solutions count source="path/to/video.mp4" # specify video file path如需了解更多 Ultralytics 解决方案的信息,请访问解决方案页面。
常见问题#
要使用 CLI 训练模型,请在终端中执行一行命令。例如,要训练检测模型 10 个周期,请运行:
yolo train data=coco8.yaml model=yolo26n.pt epochs=10此命令使用带有特定参数的
train模式。有关可用参数的完整列表,请参阅配置指南。Ultralytics YOLO CLI 支持多种任务,包括检测、分割、语义分割、深度估计、分类、姿态估计和有向边界框检测。你还可以执行以下操作:
- 训练模型:运行
yolo train data=<data.yaml> model=<model.pt> epochs=<num>。 - 运行预测:使用
yolo predict model=<model.pt> source=<data_source> imgsz=<image_size>。 - 导出模型:执行
yolo export model=<model.pt> format=<export_format>。 - 使用解决方案:运行
yolo solutions <solution_name>使用现成应用。
- 训练模型:运行
你可以将 YOLO 模型导出为多种格式,包括 ONNX、TensorRT、CoreML、TensorFlow 等。例如,要将模型导出为 ONNX 格式,请运行:
yolo export model=yolo26n.pt format=onnx导出命令支持多种选项,可针对特定部署环境优化模型。有关所有可用导出格式及其参数的完整详情,请访问导出页面。
Ultralytics 通过
solutions命令提供可直接使用的解决方案。例如,要统计视频中的对象:yolo solutions count source="path/to/video.mp4"这些解决方案只需极少配置,即可立即执行常见计算机视觉任务。要查看所有可用解决方案,请运行
yolo solutions help。每个解决方案都有可自定义的特定参数,以满足你的需求。
评论28
提出问题、分享结果,或帮助其他人。
Lishiquan12
Usage: yolo [OPTIONS] COMMAND [ARGS]... Try 'yolo -h' for help.
Error: No such command 'detect'. why?
1
Glenn JocherUltralytics嘿!看起来你在尝试使用
detect命令,但这实际上并不直接作为命令使用。😅 在YOLOv8 CLI中,detect更像是一个任务类型标识符,而不是直接使用的命令。比如说,如果你想要对一张图片进行预测(检测),你可以这样做:
yolo detect predict model=yolov8n.pt source='path/to/image.jpg'这里
detect指出你想要进行的是物体检测任务,predict是你想要进行的模式,接着是模型和图像源的具体参数。🔍确保检查 Ultralytics YOLO 文档 获取更多详细信息和参数选项!希望这有助于解决问题!
JackeShen
too
Glenn JocherUltralytics看起来你遇到了
'yolo detect' 是无效命令的问题。 😊 对于YOLOv8 CLI的用法, 实际上你不需要直接使用 "detect" 作为命令。以下是一个简单的例子,演示如何正确地使用 CLI 来运行一个预测:yolo predict model=yolov8n.pt source='path/to/your/image.jpg'在这个例子中,我们使用
predict而不是detect,然后指定模型和要进行预测的数据源。希望这能帮助到你!如果还有其他疑问,欢迎继续提问。👍
UserHello Team Ultralytics,
Good morning!
Many thanks for the great work.
Couple of questions:
- How can i generate same graphs (graphs after training) after using the trained model on my unsense samples data?
- I can use the target folder after training the model, however, it only exports the images with the prediction boxes. I want to have a pie chart or bar chart or even the same plots it exports after the training run
- For the object detection via a video, if i have 4 images to display in one second, the model looks the same image multiple times. How can we correct the frames reading?
Looking forward to your kind input,
Kind regards,
MUK
duoerku
你好,进一部沟通请联系15680550171, 或者添加微信 BK-Mike
Glenn JocherUltralytics(已编辑)@yizhihuo666 好问题!当你更新到最新版本的Ultralytics库时,不指定模型时使用的默认模型会随版本更新(现在检测任务默认为 yolo26n.pt)。这就是为什么你的原始命令会提示下载新的默认模型文件。
如果你想继续使用YOLOv8模型,可以显式指定模型路径:
yolo train model=yolov8n.pt data=your_data.yaml epochs=100如果你想使用最新的YOLO26模型(推荐),可以直接使用:
yolo train model=yolo26n.pt data=your_data.yaml epochs=100YOLO26提供了更好的性能和准确性,所以建议升级到新模型。
@duoerku 请在GitHub上提出具体的技术问题,我们会在这里为你提供支持,无法提供私人联系方式。
yizhihuo666
Thank you for your reply. As you mentioned, the system has now been updated to the YOLOv11 algorithm. I would like to know how I should proceed if I want to train the yolov8n.pt model using the YOLOv8 algorithm. Do I need to revert to a previous version of Ultralytics?
Glenn JocherUltralytics(已编辑)@yizhihuo666 You don't need to downgrade Ultralytics! The current version still fully supports YOLOv8 models. Simply specify the YOLOv8 model explicitly in your command:
yolo train model=yolov8n.pt data=your_data.yaml epochs=100The latest Ultralytics version supports both YOLOv8 and YOLO26 models - it just defaults to the current default model (
yolo26n.ptfor detection) when no model is specified. By explicitly usingmodel=yolov8n.pt, you'll train with the YOLOv8 architecture as intended.
yizhihuo666
May I ask which algorithm is used by default for training through the ultralytic command line, YOLOV8 or YOLOV11
yizhihuo666
I trained yolov8n.pt using the command line in 2023 and recently updated the latest version of the ultralytic library. I found that when I used the original command, it kept prompting me to download the yolo11n.pt file
muhammadrizwan11
I noticed some discrepancies in the training and validation commands under the CLI chapter of the Ultralytics YOLO documentation. The documented training command is written as '' yolo detect train data=coco8.yaml model=yolo11n.pt epochs=100 imgsz=640 '' but the correct command should be '' yolo train data=coco8.yaml model=yolo11n.pt epochs=10 lr0=0.01'' The word "detect" should be removed. Similarly, the validation command is written as '' yolo detect val model=yolo11n.pt'' , whereas the correct command should be '' yolo val model=yolo11n.pt data=coco8.yaml batch=1 imgsz=640 ''. Again, "detect" is unnecessary, and important parameters such as the dataset (data=coco8.yaml), batch size (batch=1), and image size (imgsz=640) are missing. These inconsistencies might cause confusion for users following the documentation. Could the team review and update this section for accuracy? i am also doing working in yolo https://github.com/muhammadrizwan11
Glenn JocherUltralytics@muhammadrizwan11 thank you for pointing this out! You're correct that the
detecttask argument is optional in CLI commands when the model type is specified, as YOLO can infer the task from the model name. Bothyolo detect trainandyolo trainsyntaxes are valid, but we'll standardize the docs to use the more concise form where possible. The validation example should indeed include explicit parameters for clarity, even thoughdatais inherited from training. We'll update the documentation to reflect these points. For reference, see the CLI Syntax section in the Ultralytics YOLO documentation.
aryakpt
HI, can you help me, how do i save the validation result if i use CLI? Because i clone github ultralytics directly
Glenn JocherUltralytics(已编辑)@aryakpt validation results (metrics and plots such as the confusion matrix) are saved to a run folder like
runs/detect/valby default. Addsave_json=Trueto also save predictions as a COCO-format JSON file:yolo val model=path/to/best.pt data=data.yaml save_json=Truearyakpt(已编辑)
thanks glenn for the response. but how can i access the val result like this using CLI? I want to save it in a variable
best_model = YOLO(f"{output_path}/train{suffix}/weights/best.pt") val_result = best_model.val(data=data, project=output_path) map50 = val_result.box.map50
Glenn JocherUltralytics(已编辑)The CLI doesn't return variables, and
save_json=Truesaves per-image predictions in COCO JSON format rather than the summary metrics. To access metrics like mAP50 programmatically, use the Python API:from ultralytics import YOLO metrics = YOLO("path/to/best.pt").val(data="data.yaml") print(metrics.box.map50)For details, see the Val mode documentation.
sakrig
Apple's NeuralEngine API accelerates models for all new Apple products with the M4 chips.
Does the IOS CLI app use the NeuralEngine for all Apple M4 products? Does Ultralytics support the M4 processor on the latest Mac, MacMini, Mac Pro, iPad, iPhone ...?
Seems straight forward to support the M4 NeuralEngine for all Apple products, but I have not tried.
Glenn JocherUltralytics@sakrig ultralytics YOLO models can be exported to CoreML format for Apple devices, which leverages Apple's native acceleration including NeuralEngine where available. For M4 support, ensure you're using the latest PyTorch versions with macOS MPS backend. See our CoreML export docs for implementation details.
ashikrasul
Is there a way to pass the hypeparameter file in CLI during training?
Glenn JocherUltralytics@arasul42 yes, you can pass a hyperparameter file in the CLI using the
cfgargument, like this:yolo train cfg=your_hyperparameters.yaml.2muhammadrizwan11
thank you so much i was confused but you give us a good thing
duoerku
你好,进一部沟通请联系15680550171, 或者添加微信 BK-Mike
Glenn JocherUltralytics@duoerku 你好!很抱歉,我们无法通过电话或微信进行交流,但我们很乐意在这个问题跟踪系统中帮助你解决任何有关Ultralytics YOLO的问题。如果你有任何技术问题或需要进一步的帮助,请随时在这里详细说明,我们会尽快给你回复。感谢你的理解,并期待你的回复。🙂
duoerku
你好,进一部沟通请联系15680550171, 或者添加微信 BK-Mike
Paula DerrengerUltralytics您好,谢谢您对Ultralytics YOLOv8的兴趣!🚀 对于技术支持和进一步的沟通,请优先利用GitHub Issues功能提出您的问题或需求,这样我们能够提供更有条理且可追踪的支持。
就您提供的信息来看,您似乎对命令行界面(CLI)的使用方法有兴趣,这里是可以通过几个简单示例来帮助您开始:
-
训练一个模型:
yolo train data=coco128.yaml model=yolov8n.pt epochs=10 lr0=0.01 -
运行预测:
yolo predict model=yolov8n-seg.pt source='https://youtu.be/LNwODJXcvt4' imgsz=320 -
验证模型:
yolo val model=yolov8n.pt data=coco128.yaml batch=1 imgsz=640 -
导出模型为ONNX格式:
yolo export model=yolov8n-cls.pt format=onnx imgsz=224,128
更多详细命令和选项,请参阅我们的官方文档。如果有更具体的问题或需求,欢迎在GitHub上开启一个issue进行讨论。🤗
-