Hugging Face's logo

qualcomm
/
YOLOv8-Detection

Object Detection
PyTorch
real_time
android
Model card Files
xet
 Community
1
qaihm-bot commited on
Commit
e28c605
·
verified ·
1 Parent(s): 00d412a

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +40 -19
README.md CHANGED
@@ -15,7 +15,7 @@ tags:
15
 
16
  Ultralytics YOLOv8 is a machine learning model that predicts bounding boxes and classes of objects in an image.
17
 
18
- This model is an implementation of YOLOv8-Detection found [here](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/detect).
19
  This repository provides scripts to run YOLOv8-Detection on Qualcomm® devices.
20
  More details on model performance across various devices, can be found
21
  [here](https://aihub.qualcomm.com/models/yolov8_det).
@@ -30,15 +30,32 @@ More details on model performance across various devices, can be found
30
  - Number of parameters: 3.18M
31
  - Model size: 12.2 MB
32
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
 
34
 
35
 
36
- | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
- | ---|---|---|---|---|---|---|---|
38
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 5.248 ms | 0 - 5 MB | FP16 | NPU | [YOLOv8-Detection.tflite](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.tflite)
39
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 5.281 ms | 4 - 16 MB | FP16 | NPU | [YOLOv8-Detection.so](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.so)
40
-
41
-
42
 
43
  ## Installation
44
 
@@ -94,16 +111,16 @@ device. This script does the following:
94
  ```bash
95
  python -m qai_hub_models.models.yolov8_det.export
96
  ```
97
-
98
  ```
99
- Profile Job summary of YOLOv8-Detection
100
- --------------------------------------------------
101
- Device: Snapdragon X Elite CRD (11)
102
- Estimated Inference Time: 5.44 ms
103
- Estimated Peak Memory Range: 4.70-4.70 MB
104
- Compute Units: NPU (285) | Total (285)
105
-
106
-
 
107
  ```
108
 
109
 
@@ -202,15 +219,19 @@ provides instructions on how to use the `.so` shared library in an Android appl
202
  Get more details on YOLOv8-Detection's performance across various devices [here](https://aihub.qualcomm.com/models/yolov8_det).
203
  Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
204
 
 
205
  ## License
206
- - The license for the original implementation of YOLOv8-Detection can be found
207
- [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).
208
- - The license for the compiled assets for on-device deployment can be found [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE)
 
209
 
210
  ## References
211
  * [Ultralytics YOLOv8 Docs: Object Detection](https://docs.ultralytics.com/tasks/detect/)
212
  * [Source Model Implementation](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/detect)
213
 
 
 
214
  ## Community
215
  * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
216
  * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
 
15
 
16
  Ultralytics YOLOv8 is a machine learning model that predicts bounding boxes and classes of objects in an image.
17
 
18
+ This model is an implementation of YOLOv8-Detection found [here]({source_repo}).
19
  This repository provides scripts to run YOLOv8-Detection on Qualcomm® devices.
20
  More details on model performance across various devices, can be found
21
  [here](https://aihub.qualcomm.com/models/yolov8_det).
 
30
  - Number of parameters: 3.18M
31
  - Model size: 12.2 MB
32
 
33
+ | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
34
+ |---|---|---|---|---|---|---|---|---|
35
+ | YOLOv8-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 5.198 ms | 0 - 163 MB | FP16 | NPU | [YOLOv8-Detection.tflite](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.tflite) |
36
+ | YOLOv8-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 5.304 ms | 5 - 20 MB | FP16 | NPU | [YOLOv8-Detection.so](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.so) |
37
+ | YOLOv8-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 6.063 ms | 5 - 10 MB | FP16 | NPU | [YOLOv8-Detection.onnx](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.onnx) |
38
+ | YOLOv8-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 3.84 ms | 0 - 92 MB | FP16 | NPU | [YOLOv8-Detection.tflite](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.tflite) |
39
+ | YOLOv8-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 3.826 ms | 5 - 53 MB | FP16 | NPU | [YOLOv8-Detection.so](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.so) |
40
+ | YOLOv8-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 5.039 ms | 5 - 114 MB | FP16 | NPU | [YOLOv8-Detection.onnx](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.onnx) |
41
+ | YOLOv8-Detection | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 5.145 ms | 0 - 2 MB | FP16 | NPU | [YOLOv8-Detection.tflite](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.tflite) |
42
+ | YOLOv8-Detection | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 4.996 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
43
+ | YOLOv8-Detection | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 5.198 ms | 0 - 4 MB | FP16 | NPU | [YOLOv8-Detection.tflite](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.tflite) |
44
+ | YOLOv8-Detection | SA8255 (Proxy) | SA8255P Proxy | QNN | 5.109 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
45
+ | YOLOv8-Detection | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 5.234 ms | 0 - 2 MB | FP16 | NPU | [YOLOv8-Detection.tflite](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.tflite) |
46
+ | YOLOv8-Detection | SA8775 (Proxy) | SA8775P Proxy | QNN | 5.085 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
47
+ | YOLOv8-Detection | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 5.156 ms | 0 - 16 MB | FP16 | NPU | [YOLOv8-Detection.tflite](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.tflite) |
48
+ | YOLOv8-Detection | SA8650 (Proxy) | SA8650P Proxy | QNN | 5.069 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
49
+ | YOLOv8-Detection | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 8.67 ms | 0 - 82 MB | FP16 | NPU | [YOLOv8-Detection.tflite](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.tflite) |
50
+ | YOLOv8-Detection | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 7.878 ms | 5 - 40 MB | FP16 | NPU | Use Export Script |
51
+ | YOLOv8-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 3.025 ms | 0 - 58 MB | FP16 | NPU | [YOLOv8-Detection.tflite](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.tflite) |
52
+ | YOLOv8-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 3.595 ms | 5 - 49 MB | FP16 | NPU | Use Export Script |
53
+ | YOLOv8-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 4.011 ms | 5 - 73 MB | FP16 | NPU | [YOLOv8-Detection.onnx](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.onnx) |
54
+ | YOLOv8-Detection | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 5.524 ms | 5 - 5 MB | FP16 | NPU | Use Export Script |
55
+ | YOLOv8-Detection | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.702 ms | 5 - 5 MB | FP16 | NPU | [YOLOv8-Detection.onnx](https://huggingface.co/qualcomm/YOLOv8-Detection/blob/main/YOLOv8-Detection.onnx) |
56
 
57
 
58
 
 
 
 
 
 
 
59
 
60
  ## Installation
61
 
 
111
  ```bash
112
  python -m qai_hub_models.models.yolov8_det.export
113
  ```
 
114
  ```
115
+ Profiling Results
116
+ ------------------------------------------------------------
117
+ YOLOv8-Detection
118
+ Device : Samsung Galaxy S23 (13)
119
+ Runtime : TFLITE
120
+ Estimated inference time (ms) : 5.2
121
+ Estimated peak memory usage (MB): [0, 163]
122
+ Total # Ops : 290
123
+ Compute Unit(s) : NPU (290 ops)
124
  ```
125
 
126
 
 
219
  Get more details on YOLOv8-Detection's performance across various devices [here](https://aihub.qualcomm.com/models/yolov8_det).
220
  Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
221
 
222
+
223
  ## License
224
+ * The license for the original implementation of YOLOv8-Detection can be found [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).
225
+ * The license for the compiled assets for on-device deployment can be found [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE)
226
+
227
+
228
 
229
  ## References
230
  * [Ultralytics YOLOv8 Docs: Object Detection](https://docs.ultralytics.com/tasks/detect/)
231
  * [Source Model Implementation](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/detect)
232
 
233
+
234
+
235
  ## Community
236
  * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
237
  * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).