yoloV8-export

from ultralytics import YOLO

# Load a model
model = YOLO("yolov8n.pt")  # load an official model
model = YOLO("path/to/best.pt")  # load a custom trained model

# Export the model
model.export(format="onnx")

yolo export model=yolov8n.pt format=onnx  # export official model
yolo export model=path/to/best.pt format=onnx  # export custom trained model

Arguments 参数

Argument	Type	Default	Description
format	str	'torchscript'	Target format for the exported model, such as 'onnx', 'torchscript', 'tensorflow', or others, defining compatibility with various deployment environments. 导出模型的目标格式，如 'onnx' 、 'torchscript' 、 'tensorflow' 或其他格式，定义与各种部署环境的兼容性。
imgsz	int or tuple	640	Desired image size for the model input. Can be an integer for square images or a tuple (height, width) for specific dimensions. 模型输入所需的图像大小。对于方形图像可以是整数，对于特定维度可以是元组 (height, width) 。
keras	bool	False	Enables export to Keras format for TensorFlow SavedModel, providing compatibility with TensorFlow serving and APIs. 支持将TensorFlow SavedModel导出为Keras格式，提供与TensorFlow服务和api的兼容性。
optimize	bool	False	Applies optimization for mobile devices when exporting to TorchScript, potentially reducing model size and improving performance. 在导出到TorchScript时，适用于移动设备的优化，可能会减小模型尺寸并提高性能。
half	bool	False	Enables FP16 (half-precision) quantization, reducing model size and potentially speeding up inference on supported hardware. 支持FP16(半精度)量化，减少模型尺寸，并可能加快对支持硬件的推理。
int8	bool	False	Activates INT8 quantization, further compressing the model and speeding up inference with minimal accuracy loss, primarily for edge devices. 激活INT8量化，进一步压缩模型并以最小的精度损失加速推理，主要用于边缘设备。
dynamic	bool	False	Allows dynamic input sizes for ONNX and TensorRT exports, enhancing flexibility in handling varying image dimensions. 允许ONNX和TensorRT导出的动态输入大小，增强处理不同图像尺寸的灵活性。
simplify	bool	False	Simplifies the model graph for ONNX exports with onnxslim, potentially improving performance and compatibility. 使用 onnxslim 简化ONNX导出的模型图，潜在地提高性能和兼容性。
opset	int	None	Specifies the ONNX opset version for compatibility with different ONNX parsers and runtimes. If not set, uses the latest supported version. 指定ONNX opset版本，以便与不同的ONNX解析器和运行时兼容。如果没有设置，则使用支持的最新版本。
workspace	float	4.0	Sets the maximum workspace size in GiB for TensorRT optimizations, balancing memory usage and performance. 为TensorRT优化设置GiB中的最大工作空间大小，平衡内存使用和性能。
nms	bool	False	Adds Non-Maximum Suppression (NMS) to the CoreML export, essential for accurate and efficient detection post-processing. 将非最大抑制(NMS)添加到CoreML导出中，这对于准确有效的检测后处理至关重要。
batch	int	1	Specifies export model batch inference size or the max number of images the exported model will process concurrently in predict mode. 指定导出模型批推理大小或导出模型将在 predict 模式下并发处理的最大图像数。

Export Formats 导出格式

Format 格式	format Argument	Model 模型	Metadata 元数据	Arguments 参数
PyTorchPy	-	yolov8n.pt	✅	-
TorchScript	torchscript	yolov8n.torchscript	✅	imgsz, optimize, batch
ONNX	onnx	yolov8n.onnx	✅	imgsz, half, dynamic, simplify, opset, batch
OpenVINO	openvino	yolov8n_openvino_model/	✅	imgsz, half, int8, batch
TensorRT	engine	yolov8n.engine	✅	imgsz, half, dynamic, simplify, workspace, int8, batch
CoreML	coreml	yolov8n.mlpackage	✅	imgsz, half, int8, nms, batch
TF SavedModel	saved_model	yolov8n_saved_model/	✅	imgsz, keras, int8, batch
TF GraphDefTF	pb	yolov8n.pb	❌	imgsz, batch
TF LiteTF	tflite	yolov8n.tflite	✅	imgsz, half, int8, batch
TF Edge TPU	edgetpu	yolov8n_edgetpu.tflite	✅	imgsz
TF.js	tfjs	yolov8n_web_model/	✅	imgsz, half, int8, batch
PaddlePaddle	paddle	yolov8n_paddle_model/	✅	imgsz, batch
NCNN	ncnn	yolov8n_ncnn_model/	✅	imgsz, half, batch