Learning path
Get started with object detection using a Jetson Orin Nano
Learn how to set up a Jetson Orin Nano with a MIPI CSI-2 camera and perform real-time object detection from live video and image files using DetectNet and TensorRT.
Evaluation Conditions
Object Detection · Raspberry Pi 5 · INT8 · 640×640 · COCO 2017 (val2017)
| Metric | Resultsvs baseline | Change | |
|---|---|---|---|
| End to end latency p50 | 2650.58ms4374.92ms | −1724.34 ms | |
| End to end latency p90 | 2652.60ms4381.05ms | −1728.46 ms | |
| End to end latency p99 | 2654.18ms4385.16ms | −1730.97 ms | |
| Peak memory | 268.14MB335.28MB | −67.14 MB | |
| Average memory | 216.14MB327.39MB | −111.25 MB | |
| Time to first inference | 2706.00ms4426.72ms | −1720.73 ms | |
| Frames per second | 0.38fps0.23fps | +0.15 fps | |
| mAP@0.50:0.95 | 52.29%52.77% | −0.48% | |
| mAP@0.50 | 68.98%69.35% | −0.37% | |
| mAP@0.75 | 56.89%57.41% | −0.52% |
Arm’s publication of the Optimized Model does not constitute an endorsement or certification of the Original Model or a representation that the Optimized Model is suitable for production use or any particular purpose.
To the fullest extent permitted by applicable law (i) the Optimized Model is provided “as is.” Arm makes no representations or warranties that the Original Model, the Optimized Model or their outputs are accurate, safe, secure, non-infringing, legally compliant, suitable for production use or fit for any particular purpose; and (ii) Arm will not be liable for any loss or damage arising from or in connection with the Optimized Model, its use or its outputs.
You are responsible for independently evaluating the Optimized Model, its outputs and its suitability for your intended use, including compliance with applicable legal, regulatory, safety and security requirements.
Arm does not commit to provide ongoing support, maintenance or updates for the Optimized Model. Any use of or reliance on the Optimized Model or its outputs is at your own risk.
Ultralytics provides Ultralytics YOLO software and models available through the Arm AI Portal under the GNU Affero General Public License v3.0 ("AGPL-3.0"), unless you have entered into a separate written license agreement with Ultralytics. Accessing, downloading, or retraining these materials through Arm AI Portal does not grant you an Ultralytics Enterprise License or any other proprietary Ultralytics license.
AGPL-3.0 requires you to release the complete source code of any application that uses Ultralytics YOLO, including applications made available over a network, under the same license. If you are embedding YOLO in a commercial product, internal tool, or production deployment and cannot open-source your code, you need an Ultralytics Enterprise License.
You are responsible for determining which applies to your use. Terms and enterprise licensing options are available at: https://www.ultralytics.com/license
Use of the Portal is subject to the Arm Website Terms and Conditions of Use.
| Configuration | Baseline | Arm Optimized |
|---|---|---|
| Dataset | COCO 2017 (val2017) | COCO 2017 (val2017) |
| Sample count | 5,000 | 5,000 |
| Batch size | 1 | 1 |
| Input resolution | 640x640 | 640x640 |
| Runs | 100 | 100 |
| Warmup runs | 10 | 10 |