Improve verbose argument description in benchmark doc (#20791)

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Lakshantha Dissanayake 2025-05-25 08:33:40 -07:00 committed by GitHub
parent 460cbff100
commit df9cce9de0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -98,7 +98,7 @@ Arguments such as `model`, `data`, `imgsz`, `half`, `device`, `verbose` and `for
| `half` | `False` | Enables FP16 (half-precision) inference, reducing memory usage and possibly increasing speed on compatible hardware. Use `half=True` to enable. |
| `int8` | `False` | Activates INT8 quantization for further optimized performance on supported devices, especially useful for edge devices. Set `int8=True` to use. |
| `device` | `None` | Defines the computation device(s) for benchmarking, such as `"cpu"` or `"cuda:0"`. |
| `verbose` | `False` | Controls the level of detail in logging output. A boolean value; set `verbose=True` for detailed logs or a float for thresholding errors. |
| `verbose` | `False` | Controls the level of detail in logging output. Set `verbose=True` for detailed logs. |
| `format` | `''` | Benchmark the model on a single export format. i.e `format=onnx` |
## Export Formats