Upload Date | November 11 2024 09:07 AM |
Views | 9 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | asus ASUSAI2501C |
Model ID | asus ASUSAI2501C |
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% |
448
83.2 IPS |
|
Image Classification (HP)
|
100% |
442
82.2 IPS |
|
Image Classification (Q)
|
99% |
1190
222.0 IPS |
|
Image Segmentation (SP)
|
100% |
564
9.14 IPS |
|
Image Segmentation (HP)
|
100% |
566
9.17 IPS |
|
Image Segmentation (Q)
|
98% |
1129
18.4 IPS |
|
Pose Estimation (SP)
|
100% |
753
0.88 IPS |
|
Pose Estimation (HP)
|
100% |
732
0.85 IPS |
|
Pose Estimation (Q)
|
98% |
2914
3.41 IPS |
|
Object Detection (SP)
|
100% |
407
32.3 IPS |
|
Object Detection (HP)
|
100% |
409
32.4 IPS |
|
Object Detection (Q)
|
87% |
1241
99.5 IPS |
|
Face Detection (SP)
|
100% |
1030
12.2 IPS |
|
Face Detection (HP)
|
100% |
1031
12.2 IPS |
|
Face Detection (Q)
|
97% |
2521
30.1 IPS |
|
Depth Estimation (SP)
|
100% |
908
7.00 IPS |
|
Depth Estimation (HP)
|
99% |
904
6.96 IPS |
|
Depth Estimation (Q)
|
64% |
2216
20.1 IPS |
|
Style Transfer (SP)
|
100% |
1557
2.00 IPS |
|
Style Transfer (HP)
|
100% |
1556
2.00 IPS |
|
Style Transfer (Q)
|
98% |
4257
5.49 IPS |
|
Image Super-Resolution (SP)
|
100% |
481
17.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
485
17.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
1763
65.3 IPS |
|
Text Classification (SP)
|
100% |
667
889.8 IPS |
|
Text Classification (HP)
|
100% |
647
864.2 IPS |
|
Text Classification (Q)
|
91% |
1082
1.45 KIPS |
|
Machine Translation (SP)
|
100% |
1036
17.8 IPS |
|
Machine Translation (HP)
|
100% |
1034
17.8 IPS |
|
Machine Translation (Q)
|
57% |
788
19.2 IPS |