HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

Add Export Arguments tables to all Export docs (#18952)

Browse source 
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Francesco Mattioli <Francesco.mttl@gmail.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Lakshantha Dissanayake 2025-02-05 18:43:02 -08:00 • committed by GitHub
parent c0a4201370
commit 39b037408f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
16 changed files with 162 additions and 33 deletions
Download patch file Download diff file Expand all files Collapse all files

15
docs/en/integrations/tensorrt.md
View file

@ -107,6 +107,21 @@ Before diving into the usage instructions, be sure to check out the range of [YO
yolo predict model=yolo11n.engine source='https://ultralytics.com/images/bus.jpg'
```
### Export Arguments
| Argument | Type | Default | Description |
| ----------- | ----------------- | ------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `format` | `str` | `engine` | Target format for the exported model, defining compatibility with various deployment environments. |
| `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. |
| `half` | `bool` | `False` | Enables FP16 (half-precision) quantization, reducing model size and potentially speeding up inference on supported hardware. |
| `int8` | `bool` | `False` | Activates INT8 quantization, further compressing the model and speeding up inference with minimal [accuracy](https://www.ultralytics.com/glossary/accuracy) loss, primarily for edge devices. |
| `dynamic` | `bool` | `False` | Allows dynamic input sizes, enhancing flexibility in handling varying image dimensions. |
| `simplify` | `bool` | `True` | Simplifies the model graph with `onnxslim`, potentially improving performance and compatibility. |
| `workspace` | `float` or `None` | `None` | Sets the maximum workspace size in GiB for TensorRT optimizations, balancing memory usage and performance; use `None` for auto-allocation by TensorRT up to device maximum. |
| `nms` | `bool` | `False` | Adds Non-Maximum Suppression (NMS), essential for accurate and efficient detection post-processing. |
| `batch` | `int` | `1` | Specifies export model batch inference size or the max number of images the exported model will process concurrently in `predict` mode. |
| `data` | `str` | `coco8.yaml` | Path to the [dataset](https://docs.ultralytics.com/datasets) configuration file (default: `coco8.yaml`), essential for quantization. |
For more details about the export process, visit the [Ultralytics documentation page on exporting](../modes/export.md).
### Exporting TensorRT with INT8 Quantization