Hugging Face's logo

aplux
/
YOLOv8

ONNX
Model card Files Community
qc903113684 commited on
Commit
9178d58
·
verified ·
1 Parent(s): 0b81e1f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +29 -8
README.md CHANGED
@@ -11,15 +11,36 @@ It is based on deep neural network for object recognition and positioning. It ru
11
 
12
  The model can be found [here](https://github.com/ultralytics/ultralytics)
13
 
 
14
 
15
  |Device|SoC|Runtime|Model|Size (pixels)|Inference Time (ms)|Precision|Compute Unit|Model Download|
16
  |:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|
17
- |AidBox QCS6490|QCS6490|QNN|YOLOv8s(cutoff)|640|11.1|INT8|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/QCS6490/cutoff_yolov8s_int8.qnn.serialized.bin)|
18
- |AidBox QCS6490|QCS6490|QNN|YOLOv8s(cutoff)|640|24.8|INT16|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/QCS6490/cutoff_yolov8s_int16.qnn.serialized.bin)|
19
- |AidBox QCS6490|QCS6490|SNPE|YOLOv8s(cutoff)|640|9.6|INT8|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/QCS6490/cutoff_yolov8s_int8_htp_snpe2.dlc)|
20
- |AidBox QCS6490|QCS6490|SNPE|YOLOv8s(cutoff)|640|22.1|INT16|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/QCS6490/cutoff_yolov8s_int16_htp_snpe2.dlc)|
 
 
 
 
21
  |AidBox GS865|QCS8250|SNPE|YOLOv8s(cutoff)|640|35|INT8|NPU|[model download]()|
22
- |APLUX QCS8550|QCS8550|QNN|YOLOv8s(cutoff)|640|8.7|INT8|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/QCS8550/cutoff_yolov8s_int8.qnn.serialized.bin)|
23
- |APLUX QCS8550|QCS8550|QNN|YOLOv8s(cutoff)|640|20.3|INT16|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/QCS8550/cutoff_yolov8s_int16.qnn.serialized.bin)|
24
- |APLUX QCS8550|QCS8550|SNPE|YOLOv8s(cutoff)|640|3.8|INT8|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/QCS8550/cutoff_yolov8s_int8_htp_snpe2.dlc)|
25
- |APLUX QCS8550|QCS8550|SNPE|YOLOv8s(cutoff)|640|9.3|INT16|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/QCS8550/cutoff_yolov8s_int16_htp_snpe2.dlc)|
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
 
12
  The model can be found [here](https://github.com/ultralytics/ultralytics)
13
 
14
+ **Performance on devices**
15
 
16
  |Device|SoC|Runtime|Model|Size (pixels)|Inference Time (ms)|Precision|Compute Unit|Model Download|
17
  |:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|
18
+ |AidBox QCS6490|QCS6490|QNN|YOLOv8s(cutoff)|640|11.1|INT8|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/Models/QCS6490/cutoff_yolov8s_int8.qnn.serialized.bin)|
19
+ |AidBox QCS6490|QCS6490|QNN|YOLOv8s(cutoff)|640|24.8|INT16|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/Models/QCS6490/cutoff_yolov8s_int16.qnn.serialized.bin)|
20
+ |AidBox QCS6490|QCS6490|SNPE|YOLOv8s(cutoff)|640|9.6|INT8|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/Models/QCS6490/cutoff_yolov8s_int8_htp_snpe2.dlc)|
21
+ |AidBox QCS6490|QCS6490|SNPE|YOLOv8s(cutoff)|640|22.1|INT16|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/Models/QCS6490/cutoff_yolov8s_int16_htp_snpe2.dlc)|
22
+ |APLUX QCS8550|QCS8550|QNN|YOLOv8s(cutoff)|640|8.7|INT8|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/Models/QCS8550/cutoff_yolov8s_int8.qnn.serialized.bin)|
23
+ |APLUX QCS8550|QCS8550|QNN|YOLOv8s(cutoff)|640|20.3|INT16|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/Models/QCS8550/cutoff_yolov8s_int16.qnn.serialized.bin)|
24
+ |APLUX QCS8550|QCS8550|SNPE|YOLOv8s(cutoff)|640|3.8|INT8|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/Models/QCS8550/cutoff_yolov8s_int8_htp_snpe2.dlc)|
25
+ |APLUX QCS8550|QCS8550|SNPE|YOLOv8s(cutoff)|640|9.3|INT16|NPU|[model download](https://huggingface.co/aidlux/YOLOv8/blob/main/Models/QCS8550/cutoff_yolov8s_int16_htp_snpe2.dlc)|
26
  |AidBox GS865|QCS8250|SNPE|YOLOv8s(cutoff)|640|35|INT8|NPU|[model download]()|
27
+
28
+ **Demo models conversion**
29
+
30
+ Demo models converted from [**AIMO(AI Model Optimizier)**](https://aidlux.com/en/product/aimo).
31
+
32
+ The source model **YOLOv5s.onnx** can be found [here](https://huggingface.co/aplux/YOLOv8/blob/main/yolov8s.onnx).
33
+
34
+ The demo model conversion step on AIMO can be found blow:
35
+
36
+ |Device|SoC|Runtime|Model|Size (pixels)|Precision|Compute Unit|AIMO Conversion Steps|
37
+ |:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|
38
+ |AidBox QCS6490|QCS6490|QNN|YOLOv8s(cutoff)|640|INT8|NPU|[View Steps](https://huggingface.co/aplux/YOLOv8/blob/main/AIMO/QCS6490/aimo_yolov8s_qnn_int8.png)|
39
+ |AidBox QCS6490|QCS6490|QNN|YOLOv8s(cutoff)|640|INT16|NPU|[View Steps](https://huggingface.co/aplux/YOLOv8/blob/main/AIMO/QCS6490/aimo_yolov8s_qnn_int16.png)|
40
+ |AidBox QCS6490|QCS6490|SNPE|YOLOv8s(cutoff)|640|INT8|NPU|[View Steps](https://huggingface.co/aplux/YOLOv8/blob/main/AIMO/QCS6490/aimo_yolov8s_snpe_int8.png)|
41
+ |AidBox QCS6490|QCS6490|SNPE|YOLOv8s(cutoff)|640|INT16|NPU|[View Steps](https://huggingface.co/aplux/YOLOv8/blob/main/AIMO/QCS6490/aimo_yolov8s_snpe_int16.png)|
42
+ |APLUX QCS8550|QCS8550|QNN|YOLOv8s(cutoff)|640|INT8|NPU|[View Steps](https://huggingface.co/aplux/YOLOv8/blob/main/AIMO/QCS8550/aimo_yolov8s_qnn_int8.png)|
43
+ |APLUX QCS8550|QCS8550|QNN|YOLOv8s(cutoff)|640|INT16|NPU|[View Steps](https://huggingface.co/aplux/YOLOv8/blob/main/AIMO/QCS8550/aimo_yolov8s_qnn_int16.png)|
44
+ |APLUX QCS8550|QCS8550|SNPE|YOLOv8s(cutoff)|640|INT8|NPU|[View Steps](https://huggingface.co/aplux/YOLOv8/blob/main/AIMO/QCS8550/aimo_yolov8s_snpe_int8.png)|
45
+ |APLUX QCS8550|QCS8550|SNPE|YOLOv8s(cutoff)|640|INT16|NPU|[View Steps](https://huggingface.co/aplux/YOLOv8/blob/main/AIMO/QCS8550/aimo_yolov8s_snpe_int16.png)|
46
+ |AidBox GS865|QCS8250|SNPE|YOLOv8s(cutoff)|640|INT8|NPU|[View Steps]()|