Downloads · 30 days
0
huochai67/wd-convnext-tagger-v3-rk3566-int8
wd-convnext-tagger-v3-rk3566-int8 is a machine learning model from huochai67. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
INT8 RKNN conversion of SmilingWolf/wd-convnext-tagger-v3 for Rockchip RK3566 NPU inference.
Downloads · 30 days
0
Access
Public
Updated Jul 26, 2026
Repo size
107 MB
Likes
0
Public
Click a slice to open those files.
.rknn107 MB · 100%
From the Hugging Face model README
INT8 RKNN conversion of SmilingWolf/wd-convnext-tagger-v3 for Rockchip RK3566 NPU inference.
wd-convnext-tagger-v3-rk3566-int8.rknn: static-shape RK3566 modelselected_tags.csv: matching WD v3 tag metadata[1, 3, 448, 448], BGR, range 0..255Calibration images and the original ONNX model are not included.
Measured on RK3566 with 4GB RAM, RKNN Runtime 2.3.2, and driver 0.9.8:
| Metric | Result |
|---|---|
| Average NPU inference | 0.709 s/image |
| Throughput | 1.41 images/s |
| Peak process RSS | 345 MiB |
The complete conversion and board-side inference code is available at:
https://github.com/huochai67/wd-convnext-rknn-rk3566
Use selected_tags.csv from this repository with this .rknn model. Do not
mix it with labels from another WD model.
The base model is licensed under Apache-2.0. Refer to the base model and the conversion repository for attribution and deployment details.