Upload Date | November 19 2024 03:59 AM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | asus ASUSAI2501E |
Model ID | asus ASUSAI2501E |
Motherboard | sun |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 3 part 1 revision 4 |
Base Frequency | 3.53 GHz |
Cluster 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.32 GHz |
Memory Information | |
---|---|
Size | 22.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
455
84.7 IPS |
|
Image Classification (HP)
|
100% |
463
86.2 IPS |
|
Image Classification (Q)
|
99% |
1205
224.7 IPS |
|
Image Segmentation (SP)
|
100% |
600
9.73 IPS |
|
Image Segmentation (HP)
|
100% |
600
9.72 IPS |
|
Image Segmentation (Q)
|
98% |
1182
19.2 IPS |
|
Pose Estimation (SP)
|
100% |
793
0.93 IPS |
|
Pose Estimation (HP)
|
100% |
773
0.90 IPS |
|
Pose Estimation (Q)
|
98% |
3088
3.61 IPS |
|
Object Detection (SP)
|
100% |
436
34.6 IPS |
|
Object Detection (HP)
|
100% |
438
34.8 IPS |
|
Object Detection (Q)
|
87% |
1316
105.5 IPS |
|
Face Detection (SP)
|
100% |
1073
12.7 IPS |
|
Face Detection (HP)
|
100% |
1076
12.8 IPS |
|
Face Detection (Q)
|
97% |
2676
31.9 IPS |
|
Depth Estimation (SP)
|
100% |
940
7.24 IPS |
|
Depth Estimation (HP)
|
99% |
943
7.27 IPS |
|
Depth Estimation (Q)
|
64% |
2344
21.3 IPS |
|
Style Transfer (SP)
|
100% |
1633
2.10 IPS |
|
Style Transfer (HP)
|
100% |
1625
2.09 IPS |
|
Style Transfer (Q)
|
98% |
4527
5.84 IPS |
|
Image Super-Resolution (SP)
|
100% |
512
18.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
516
19.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
1881
69.7 IPS |
|
Text Classification (SP)
|
100% |
690
921.6 IPS |
|
Text Classification (HP)
|
100% |
692
923.3 IPS |
|
Text Classification (Q)
|
91% |
1094
1.47 KIPS |
|
Machine Translation (SP)
|
100% |
1096
18.9 IPS |
|
Machine Translation (HP)
|
100% |
1093
18.8 IPS |
|
Machine Translation (Q)
|
57% |
838
20.5 IPS |