Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,17 @@ Positioned above the nano model, YOLO26s provides improved representational capa
|
|
| 7 |
|
| 8 |
YOLO26s is pretrained on the **COCO dataset** and is well-suited for production object detection pipelines that require both responsiveness and reliability.
|
| 9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
## Features
|
| 11 |
- **Small model size** with balanced speed and accuracy
|
| 12 |
- **End-to-end detection** with NMS-free inference
|
|
|
|
| 7 |
|
| 8 |
YOLO26s is pretrained on the **COCO dataset** and is well-suited for production object detection pipelines that require both responsiveness and reliability.
|
| 9 |
|
| 10 |
+
## Quickstart
|
| 11 |
+
1. **Install [NexaSDK](https://sdk.nexa.ai)** and create a free account at [sdk.nexa.ai](https://sdk.nexa.ai)
|
| 12 |
+
2. **Activate your device** with your access token:
|
| 13 |
+
```bash
|
| 14 |
+
nexa config set license '<access_token>'
|
| 15 |
+
```
|
| 16 |
+
3. Run the model on Qualcomm NPU in one line:
|
| 17 |
+
```bash
|
| 18 |
+
nexa infer NexaAI/yolo26s-npu
|
| 19 |
+
```
|
| 20 |
+
|
| 21 |
## Features
|
| 22 |
- **Small model size** with balanced speed and accuracy
|
| 23 |
- **End-to-end detection** with NMS-free inference
|