Specify RKNN Toolkit2 version

README.md

@@ -12,7 +12,7 @@ tags:
 
 Converted with the Ultralytics export workflow and task-specific RKNN conversion tools. This repository contains 100 FP16 and INT8 exports for RK3576 and RK3588. Tasks include classify, detect, obb, pose, segment.
 
-Choose a model under `models/<task>/<checkpoint>/<chip>/<precision>/` and download both `model.rknn` and `metadata.yaml`. The [manifest](manifest.json) lists the supported combinations and SHA-256 hashes.
+Choose a model under `models/<task>/<variant>/<chip>/<precision>/` and download both `model.rknn` and `metadata.yaml`. The [manifest](manifest.json) lists the supported combinations and SHA-256 hashes.
 
 ## Source and license
 
@@ -20,4 +20,4 @@ The inputs are official Ultralytics checkpoints. Conversion changed the file for
 
 Run `python source/convert-model.py --help`. For a detection INT8 export, pass a COCO128 dataset YAML. For other INT8 tasks, pass a COCO128 image list. Use `--calibration-limit 128` and the input size in the manifest.
 
-The [source directory](tree/main/source) contains the original checkpoints, conversion scripts, and environment and calibration records. Upstream Ultralytics source is available from [PyPI](https://pypi.org/project/ultralytics/#history). The conversion also uses [RKNN Toolkit2](https://github.com/airockchip/rknn-toolkit2), available separately from Rockchip.
+The [source directory](tree/main/source) contains the original checkpoints, conversion scripts, and environment and calibration records. Upstream Ultralytics source is available from [PyPI](https://pypi.org/project/ultralytics/#history). The conversion used RKNN Toolkit2 2.3.2. See [RKNN Toolkit2](https://github.com/airockchip/rknn-toolkit2), available separately from Rockchip.