# Rockchip

Models are located at the [Rockchip model zoo on the AI Hub](https://hub.degirum.com/public-models/degirum/rockchip?utm_source=docs.degirum.com\&utm_medium=site\&utm_campaign=ai-hub-public-models-rockchip).

## Models by DeGirum

### RK3566

**Age Estimation**

| Model Name                                           | Use Case       | MAE   | MSE    |
| ---------------------------------------------------- | -------------- | ----- | ------ |
| yolov8n\_relu6\_age--256x256\_quant\_rknn\_rk3566\_1 | Age Estimation | 4.772 | 39.965 |

**Classification**

| Model Name                                               | Use Case       | Top‑1 | Top‑5 |
| -------------------------------------------------------- | -------------- | ----- | ----- |
| yolov8s\_silu\_imagenet--224x224\_quant\_rknn\_rk3566\_1 | Classification |       |       |

**Detection**

| Model Name                                                        | Use Case                                      | mAP 50‑95                              | mAP 50                                 |
| ----------------------------------------------------------------- | --------------------------------------------- | -------------------------------------- | -------------------------------------- |
| yolov10n--640x640\_float\_rknn\_rk3566\_1                         | Detection                                     |                                        |                                        |
| yolov10n--640x640\_quant\_rknn\_rk3566\_1                         | Detection                                     |                                        |                                        |
| yolov8n\_relu6\_car--640x640\_quant\_rknn\_rk3566\_1              | Car Detection                                 | 67.847                                 | 85.51                                  |
| yolov8n\_relu6\_coco--640x640\_quant\_rknn\_rk3566\_1             | COCO Detection                                | 35.157                                 | 50.248                                 |
| yolov8n\_relu6\_coco\_pose--640x640\_quant\_rknn\_rk3566\_1       | COCO Pose Keypoints                           |                                        |                                        |
| yolov8n\_relu6\_coco\_seg--640x640\_quant\_rknn\_rk3566\_1        | COCO Instance Segmentation                    | <p>bbox: 34.315</p><p>mask: 28.387</p> | <p>bbox: 49.027</p><p>mask: 46.028</p> |
| yolov8n\_relu6\_face--640x640\_quant\_rknn\_rk3566\_1             | Face Detection                                | 56.784                                 | 78.782                                 |
| yolov8n\_relu6\_fairface\_gender--256x256\_quant\_rknn\_rk3566\_1 | Gender Classification                         |                                        |                                        |
| yolov8n\_relu6\_hand--640x640\_quant\_rknn\_rk3566\_1             | Hand Detection                                | 45.012                                 | 76.201                                 |
| yolov8n\_relu6\_human\_head--640x640\_quant\_rknn\_rk3566\_1      | Human Head Detection                          |                                        |                                        |
| yolov8n\_relu6\_lp--640x640\_quant\_rknn\_rk3566\_1               | License Plate Detection                       | 56.194                                 | 86.072                                 |
| yolov8n\_relu6\_person--640x640\_float\_rknn\_rk3566\_1           | Person Detection                              | 31.266                                 | 50.870                                 |
| yolov8n\_relu6\_person--640x640\_quant\_rknn\_rk3566\_1           | Person Detection                              | 27.968                                 | 46.866                                 |
| yolov8n\_relu6\_ppe--640x640\_quant\_rknn\_rk3566\_1              | Personal Protective Equipment (PPE) Detection | 36.165                                 | 67.714                                 |
| yolov8n\_relu6\_widerface\_kpts--640x640\_quant\_rknn\_rk3566\_1  | Face Detection with Five Keypoints            |                                        |                                        |
| yolov8n\_silu\_coco--640x640\_quant\_rknn\_rk3566\_1              | COCO Detection                                | 36.771                                 | 51.872                                 |
| yolov9t--640x640\_float\_rknn\_rk3566\_1                          | Detection                                     |                                        |                                        |
| yolov9t--640x640\_quant\_rknn\_rk3566\_1                          | Detection                                     |                                        |                                        |

### RK3568

**Age Estimation**

| Model Name                                           | Use Case       | MAE   | MSE    |
| ---------------------------------------------------- | -------------- | ----- | ------ |
| yolov8n\_relu6\_age--256x256\_quant\_rknn\_rk3568\_1 | Age Estimation | 4.772 | 39.965 |

**Classification**

| Model Name                                               | Use Case       | Top‑1 | Top‑5 |
| -------------------------------------------------------- | -------------- | ----- | ----- |
| yolov8s\_silu\_imagenet--224x224\_quant\_rknn\_rk3568\_1 | Classification |       |       |

**Detection**

| Model Name                                                        | Use Case                                      | mAP 50‑95                              | mAP 50                                 |
| ----------------------------------------------------------------- | --------------------------------------------- | -------------------------------------- | -------------------------------------- |
| yolov10n--640x640\_float\_rknn\_rk3568\_1                         | Detection                                     |                                        |                                        |
| yolov10n--640x640\_quant\_rknn\_rk3568\_1                         | Detection                                     |                                        |                                        |
| yolov8n\_relu6\_car--640x640\_quant\_rknn\_rk3568\_1              | Car Detection                                 | 67.847                                 | 85.51                                  |
| yolov8n\_relu6\_coco--640x640\_quant\_rknn\_rk3568\_1             | COCO Detection                                | 35.157                                 | 50.248                                 |
| yolov8n\_relu6\_coco\_pose--640x640\_quant\_rknn\_rk3568\_1       | COCO Pose Keypoints                           |                                        |                                        |
| yolov8n\_relu6\_coco\_seg--640x640\_quant\_rknn\_rk3568\_1        | COCO Instance Segmentation                    | <p>bbox: 34.315</p><p>mask: 28.387</p> | <p>bbox: 49.027</p><p>mask: 46.028</p> |
| yolov8n\_relu6\_face--640x640\_quant\_rknn\_rk3568\_1             | Face Detection                                | 56.784                                 | 78.782                                 |
| yolov8n\_relu6\_fairface\_gender--256x256\_quant\_rknn\_rk3568\_1 | Gender Classification                         |                                        |                                        |
| yolov8n\_relu6\_fire\_smoke--640x640\_quant\_rknn\_rk3568\_1      | Fire & Smoke Detection                        |                                        |                                        |
| yolov8n\_relu6\_hand--640x640\_quant\_rknn\_rk3568\_1             | Hand Detection                                | 45.012                                 | 76.201                                 |
| yolov8n\_relu6\_human\_head--640x640\_quant\_rknn\_rk3568\_1      | Human Head Detection                          |                                        |                                        |
| yolov8n\_relu6\_lp--640x640\_quant\_rknn\_rk3568\_1               | License Plate Detection                       | 56.194                                 | 86.072                                 |
| yolov8n\_relu6\_person--640x640\_float\_rknn\_rk3568\_1           | Person Detection                              | 31.997                                 | 51.401                                 |
| yolov8n\_relu6\_person--640x640\_quant\_rknn\_rk3568\_1           | Person Detection                              | 27.968                                 | 46.866                                 |
| yolov8n\_relu6\_ppe--640x640\_quant\_rknn\_rk3568\_1              | Personal Protective Equipment (PPE) Detection | 36.165                                 | 67.714                                 |
| yolov8n\_relu6\_widerface\_kpts--640x640\_quant\_rknn\_rk3568\_1  | Face Detection with Five Keypoints            |                                        |                                        |
| yolov8n\_silu\_coco--640x640\_quant\_rknn\_rk3568\_1              | COCO Detection                                | 36.771                                 | 51.872                                 |
| yolov9t--640x640\_float\_rknn\_rk3568\_1                          | Detection                                     |                                        |                                        |
| yolov9t--640x640\_quant\_rknn\_rk3568\_1                          | Detection                                     |                                        |                                        |

### RK3588

**Age Estimation**

| Model Name                                           | Use Case       | MAE   | MSE    |
| ---------------------------------------------------- | -------------- | ----- | ------ |
| yolov8n\_relu6\_age--256x256\_quant\_rknn\_rk3588\_1 | Age Estimation | 4.772 | 39.965 |

**Classification**

| Model Name                                               | Use Case       | Top‑1 | Top‑5 |
| -------------------------------------------------------- | -------------- | ----- | ----- |
| yolov8s\_silu\_imagenet--224x224\_quant\_rknn\_rk3588\_1 | Classification |       |       |

**Detection**

| Model Name                                                        | Use Case                                      | mAP 50‑95                              | mAP 50                                 |
| ----------------------------------------------------------------- | --------------------------------------------- | -------------------------------------- | -------------------------------------- |
| yolov5n\_relu6\_coco--640x640\_float\_rknn\_rk3588\_1             | COCO Detection                                | 25.33                                  | 42.05                                  |
| yolov5n\_relu6\_coco--640x640\_quant\_rknn\_rk3588\_1             | COCO Detection                                | 24.89                                  | 41.75                                  |
| yolov5s\_relu6\_coco--640x640\_float\_rknn\_rk3588\_1             | COCO Detection                                | 35.47                                  | 54.15                                  |
| yolov5s\_relu6\_coco--640x640\_quant\_rknn\_rk3588\_1             | COCO Detection                                | 34.88                                  | 53.82                                  |
| yolov5m\_relu6\_coco--640x640\_float\_rknn\_rk3588\_1             | COCO Detection                                | 42.35                                  | 60.46                                  |
| yolov5m\_relu6\_coco--640x640\_quant\_rknn\_rk3588\_1             | COCO Detection                                | 41.65                                  | 60.34                                  |
| yolov10n--640x640\_quant\_rknn\_rk3588\_1                         | Detection                                     |                                        |                                        |
| yolov8n\_relu6\_car--640x640\_quant\_rknn\_rk3588\_1              | Car Detection                                 | 67.847                                 | 85.51                                  |
| yolov8n\_relu6\_coco--640x640\_quant\_rknn\_rk3588\_1             | COCO Detection                                | 35.157                                 | 50.248                                 |
| yolov8n\_relu6\_coco\_pose--640x640\_quant\_rknn\_rk3588\_1       | COCO Pose Keypoints                           |                                        |                                        |
| yolov8n\_relu6\_coco\_seg--640x640\_quant\_rknn\_rk3588\_1        | COCO Instance Segmentation                    | <p>bbox: 34.315</p><p>mask: 28.387</p> | <p>bbox: 49.027</p><p>mask: 46.028</p> |
| yolov8n\_relu6\_face--640x640\_quant\_rknn\_rk3588\_1             | Face Detection                                | 56.784                                 | 78.782                                 |
| yolov8n\_relu6\_fairface\_gender--256x256\_quant\_rknn\_rk3588\_1 | Gender Classification                         |                                        |                                        |
| yolov8n\_relu6\_fire\_smoke--640x640\_quant\_rknn\_rk3588\_1      | Fire & Smoke Detection                        |                                        |                                        |
| yolov8n\_relu6\_hand--640x640\_quant\_rknn\_rk3588\_1             | Hand Detection                                | 45.012                                 | 76.201                                 |
| yolov8n\_relu6\_human\_head--640x640\_quant\_rknn\_rk3588\_1      | Human Head Detection                          |                                        |                                        |
| yolov8n\_relu6\_lp--640x640\_quant\_rknn\_rk3588\_1               | License Plate Detection                       | 56.194                                 | 86.072                                 |
| yolov8n\_relu6\_person--640x640\_float\_rknn\_rk3588\_1           | Person Detection                              | 31.997                                 | 51.405                                 |
| yolov8n\_relu6\_person--640x640\_quant\_rknn\_rk3588\_1           | Person Detection                              | 27.968                                 | 46.866                                 |
| yolov8n\_relu6\_ppe--640x640\_quant\_rknn\_rk3588\_1              | Personal Protective Equipment (PPE) Detection | 36.165                                 | 67.714                                 |
| yolov8n\_relu6\_widerface\_kpts--640x640\_quant\_rknn\_rk3588\_1  | Face Detection with Five Keypoints            |                                        |                                        |
| yolov8n\_silu\_coco--640x640\_quant\_rknn\_rk3588\_1              | COCO Detection                                | 36.771                                 | 51.872                                 |
| yolov9t--640x640\_quant\_rknn\_rk3588\_1                          | Detection                                     |                                        |                                        |


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.degirum.com/ai-hub/public-models/rockchip.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.