Upload Date | November 14 2024 08:34 PM |
Views | 3 |
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% |
457
85.0 IPS |
|
Image Classification (HP)
|
100% |
463
86.0 IPS |
|
Image Classification (Q)
|
99% |
1210
225.8 IPS |
|
Image Segmentation (SP)
|
100% |
597
9.68 IPS |
|
Image Segmentation (HP)
|
100% |
599
9.72 IPS |
|
Image Segmentation (Q)
|
98% |
1186
19.3 IPS |
|
Pose Estimation (SP)
|
100% |
787
0.92 IPS |
|
Pose Estimation (HP)
|
100% |
766
0.89 IPS |
|
Pose Estimation (Q)
|
98% |
3067
3.59 IPS |
|
Object Detection (SP)
|
100% |
431
34.2 IPS |
|
Object Detection (HP)
|
100% |
434
34.5 IPS |
|
Object Detection (Q)
|
87% |
1310
105.0 IPS |
|
Face Detection (SP)
|
100% |
1062
12.6 IPS |
|
Face Detection (HP)
|
100% |
1079
12.8 IPS |
|
Face Detection (Q)
|
97% |
2654
31.7 IPS |
|
Depth Estimation (SP)
|
100% |
947
7.30 IPS |
|
Depth Estimation (HP)
|
99% |
948
7.30 IPS |
|
Depth Estimation (Q)
|
64% |
2332
21.2 IPS |
|
Style Transfer (SP)
|
100% |
1618
2.08 IPS |
|
Style Transfer (HP)
|
100% |
1613
2.07 IPS |
|
Style Transfer (Q)
|
98% |
4463
5.75 IPS |
|
Image Super-Resolution (SP)
|
100% |
502
18.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
507
18.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
1821
67.5 IPS |
|
Text Classification (SP)
|
100% |
685
914.0 IPS |
|
Text Classification (HP)
|
100% |
692
923.8 IPS |
|
Text Classification (Q)
|
91% |
1095
1.47 KIPS |
|
Machine Translation (SP)
|
100% |
1078
18.6 IPS |
|
Machine Translation (HP)
|
100% |
1074
18.5 IPS |
|
Machine Translation (Q)
|
57% |
826
20.2 IPS |