单目3D初始代码

docs/en/reference/utils/export/engine.md

@@ -0,0 +1,20 @@
+---
+description: TensorRT engine export utilities for converting ONNX models to optimized TensorRT engines. Provides functions for ONNX export from PyTorch models and TensorRT engine generation with support for FP16/INT8 quantization, dynamic shapes, DLA acceleration, and INT8 calibration for NVIDIA GPU inference optimization.
+keywords: Ultralytics, TensorRT export, ONNX export, PyTorch to ONNX, quantization, FP16, INT8, dynamic shapes, DLA acceleration, GPU inference, model optimization, calibration, NVIDIA, inference engine, model export
+---
+
+# Reference for `ultralytics/utils/export/engine.py`
+
+!!! success "Improvements"
+
+    This page is sourced from [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/export/engine.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/export/engine.py). Have an improvement or example to add? Open a [Pull Request](https://docs.ultralytics.com/help/contributing/) — thank you! 🙏
+
+<br>
+
+## ::: ultralytics.utils.export.engine.torch2onnx
+
+<br><br><hr><br>
+
+## ::: ultralytics.utils.export.engine.onnx2engine
+
+<br><br>

docs/en/reference/utils/export/executorch.md

@@ -0,0 +1,24 @@
+---
+description: Explore the Ultralytics ExecuTorch export utility for converting YOLO models to ExecuTorch (.pte) format for efficient on-device inference on mobile and edge devices.
+keywords: Ultralytics, ExecuTorch, YOLO, model export, PyTorch, edge AI, mobile deployment, on-device inference, XNNPACK, pte format, embedded systems
+---
+
+# Reference for `ultralytics/utils/export/executorch.py`
+
+!!! success "Improvements"
+
+    This page is sourced from [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/export/executorch.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/export/executorch.py). Have an improvement or example to add? Open a [Pull Request](https://docs.ultralytics.com/help/contributing/) — thank you! 🙏
+
+<br>
+
+## ::: ultralytics.utils.export.executorch.executorch_wrapper
+
+<br><br><hr><br>
+
+## ::: ultralytics.utils.export.executorch._executorch_kpts_decode
+
+<br><br><hr><br>
+
+## ::: ultralytics.utils.export.executorch.torch2executorch
+
+<br><br>

docs/en/reference/utils/export/imx.md

@@ -0,0 +1,36 @@
+---
+description: Learn how to export PyTorch models to Sony IMX format using Ultralytics utilities. Comprehensive guide for configurations and precision optimizations.
+keywords: Ultralytics, YOLO, export, Sony IMX, PyTorch, model conversion, INT8, machine learning, NMS, Detect, Pose
+---
+
+# Reference for `ultralytics/utils/export/imx.py`
+
+!!! success "Improvements"
+
+    This page is sourced from [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/export/imx.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/export/imx.py). Have an improvement or example to add? Open a [Pull Request](https://docs.ultralytics.com/help/contributing/) — thank you! 🙏
+
+<br>
+
+## ::: ultralytics.utils.export.imx.FXModel
+
+<br><br><hr><br>
+
+## ::: ultralytics.utils.export.imx.NMSWrapper
+
+<br><br><hr><br>
+
+## ::: ultralytics.utils.export.imx._inference
+
+<br><br><hr><br>
+
+## ::: ultralytics.utils.export.imx.pose_forward
+
+<br><br><hr><br>
+
+## ::: ultralytics.utils.export.imx.segment_forward
+
+<br><br><hr><br>
+
+## ::: ultralytics.utils.export.imx.torch2imx
+
+<br><br>

docs/en/reference/utils/export/tensorflow.md

@@ -0,0 +1,44 @@
+---
+description: TensorFlow export utilities for converting PyTorch models to various TensorFlow formats. Provides functions for converting models to TensorFlow SavedModel, Protocol Buffer (.pb), TensorFlow Lite, Edge TPU, and TensorFlow.js formats via ONNX intermediate representation with support for INT8 quantization and calibration.
+keywords: Ultralytics, TensorFlow, SavedModel, Protocol Buffer, TensorFlow Lite, TFLite, Edge TPU, TensorFlow.js, ONNX conversion, PyTorch to TensorFlow, INT8 quantization, model calibration, frozen graph, onnx2tf, model export, web deployment, mobile deployment
+---
+
+# Reference for `ultralytics/utils/export/tensorflow.py`
+
+!!! success "Improvements"
+
+    This page is sourced from [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/export/tensorflow.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/export/tensorflow.py). Have an improvement or example to add? Open a [Pull Request](https://docs.ultralytics.com/help/contributing/) — thank you! 🙏
+
+<br>
+
+## ::: ultralytics.utils.export.tensorflow.tf_wrapper
+
+<br><br><hr><br>
+
+## ::: ultralytics.utils.export.tensorflow._tf_decode_boxes
+
+<br><br><hr><br>
+
+## ::: ultralytics.utils.export.tensorflow._tf_kpts_decode
+
+<br><br><hr><br>
+
+## ::: ultralytics.utils.export.tensorflow.onnx2saved_model
+
+<br><br><hr><br>
+
+## ::: ultralytics.utils.export.tensorflow.keras2pb
+
+<br><br><hr><br>
+
+## ::: ultralytics.utils.export.tensorflow.tflite2edgetpu
+
+<br><br><hr><br>
+
+## ::: ultralytics.utils.export.tensorflow.pb2tfjs
+
+<br><br><hr><br>
+
+## ::: ultralytics.utils.export.tensorflow.gd_outputs
+
+<br><br>