Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -11,7 +11,7 @@ tags:
|
|
11 |
![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolov8_det/web-assets/model_demo.png)
|
12 |
|
13 |
# YOLOv8-Detection: Optimized for Mobile Deployment
|
14 |
-
## Real-time object detection optimized for mobile and edge
|
15 |
|
16 |
Ultralytics YOLOv8 is a machine learning model that predicts bounding boxes and classes of objects in an image.
|
17 |
|
@@ -33,8 +33,8 @@ More details on model performance across various devices, can be found
|
|
33 |
|
34 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
35 |
| ---|---|---|---|---|---|---|---|
|
36 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 9.
|
37 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 7.
|
38 |
|
39 |
|
40 |
## Installation
|
@@ -95,23 +95,23 @@ python -m qai_hub_models.models.yolov8_det.export
|
|
95 |
```
|
96 |
Profile Job summary of YOLOv8-Detection
|
97 |
--------------------------------------------------
|
98 |
-
Device: Samsung Galaxy
|
99 |
-
Estimated Inference Time:
|
100 |
-
Estimated Peak Memory Range: 0.
|
101 |
Compute Units: NPU (300) | Total (300)
|
102 |
|
103 |
Profile Job summary of YOLOv8-Detection
|
104 |
--------------------------------------------------
|
105 |
-
Device: Samsung Galaxy
|
106 |
-
Estimated Inference Time:
|
107 |
-
Estimated Peak Memory Range: 4.
|
108 |
Compute Units: NPU (294) | Total (294)
|
109 |
|
110 |
|
111 |
```
|
112 |
## How does this work?
|
113 |
|
114 |
-
This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/
|
115 |
leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model
|
116 |
on-device. Lets go through each step below in detail:
|
117 |
|
@@ -224,6 +224,7 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
|
|
224 |
## License
|
225 |
- The license for the original implementation of YOLOv8-Detection can be found
|
226 |
[here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).
|
|
|
227 |
|
228 |
## References
|
229 |
* [Real-Time Flying Object Detection with YOLOv8](https://arxiv.org/abs/2305.09972)
|
|
|
11 |
![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolov8_det/web-assets/model_demo.png)
|
12 |
|
13 |
# YOLOv8-Detection: Optimized for Mobile Deployment
|
14 |
+
## Real-time object detection optimized for mobile and edge by Ultralytics
|
15 |
|
16 |
Ultralytics YOLOv8 is a machine learning model that predicts bounding boxes and classes of objects in an image.
|
17 |
|
|
|
33 |
|
34 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
35 |
| ---|---|---|---|---|---|---|---|
|
36 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 9.217 ms | 0 - 18 MB | FP16 | NPU | [YOLOv8-Detection.tflite](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.tflite)
|
37 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 7.039 ms | 5 - 18 MB | FP16 | NPU | [YOLOv8-Detection.so](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.so)
|
38 |
|
39 |
|
40 |
## Installation
|
|
|
95 |
```
|
96 |
Profile Job summary of YOLOv8-Detection
|
97 |
--------------------------------------------------
|
98 |
+
Device: Samsung Galaxy S24 (14)
|
99 |
+
Estimated Inference Time: 6.50 ms
|
100 |
+
Estimated Peak Memory Range: 0.02-79.98 MB
|
101 |
Compute Units: NPU (300) | Total (300)
|
102 |
|
103 |
Profile Job summary of YOLOv8-Detection
|
104 |
--------------------------------------------------
|
105 |
+
Device: Samsung Galaxy S24 (14)
|
106 |
+
Estimated Inference Time: 4.84 ms
|
107 |
+
Estimated Peak Memory Range: 4.72-117.70 MB
|
108 |
Compute Units: NPU (294) | Total (294)
|
109 |
|
110 |
|
111 |
```
|
112 |
## How does this work?
|
113 |
|
114 |
+
This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/YOLOv8-Detection/export.py)
|
115 |
leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model
|
116 |
on-device. Lets go through each step below in detail:
|
117 |
|
|
|
224 |
## License
|
225 |
- The license for the original implementation of YOLOv8-Detection can be found
|
226 |
[here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).
|
227 |
+
- The license for the compiled assets for on-device deployment can be found [here]({deploy_license_url})
|
228 |
|
229 |
## References
|
230 |
* [Real-Time Flying Object Detection with YOLOv8](https://arxiv.org/abs/2305.09972)
|