Upload Date | November 18 2024 02:10 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Nothing A015 |
Model ID | Nothing A015 |
Motherboard | Tetris |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 4 Cores @ 2.50 GHz |
Memory Information | |
---|---|
Size | 5.32 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
465
86.5 IPS |
|
Image Classification (HP)
|
100% |
466
86.7 IPS |
|
Image Classification (Q)
|
100% |
1483
275.9 IPS |
|
Image Segmentation (SP)
|
100% |
541
8.76 IPS |
|
Image Segmentation (HP)
|
100% |
549
8.90 IPS |
|
Image Segmentation (Q)
|
98% |
1716
27.9 IPS |
|
Pose Estimation (SP)
|
100% |
1975
2.30 IPS |
|
Pose Estimation (HP)
|
100% |
1996
2.33 IPS |
|
Pose Estimation (Q)
|
84% |
3875
4.60 IPS |
|
Object Detection (SP)
|
100% |
447
35.5 IPS |
|
Object Detection (HP)
|
100% |
453
35.9 IPS |
|
Object Detection (Q)
|
83% |
1423
115.0 IPS |
|
Face Detection (SP)
|
100% |
1053
12.5 IPS |
|
Face Detection (HP)
|
100% |
1055
12.5 IPS |
|
Face Detection (Q)
|
95% |
3454
41.2 IPS |
|
Depth Estimation (SP)
|
100% |
1480
11.4 IPS |
|
Depth Estimation (HP)
|
99% |
1531
11.8 IPS |
|
Depth Estimation (Q)
|
64% |
3516
32.2 IPS |
|
Style Transfer (SP)
|
89% |
3622
4.70 IPS |
|
Style Transfer (HP)
|
89% |
3678
4.77 IPS |
|
Style Transfer (Q)
|
98% |
8070
10.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
816
30.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
832
30.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
1937
71.8 IPS |
|
Text Classification (SP)
|
100% |
492
657.1 IPS |
|
Text Classification (HP)
|
100% |
486
649.3 IPS |
|
Text Classification (Q)
|
88% |
902
1.22 KIPS |
|
Machine Translation (SP)
|
100% |
729
12.6 IPS |
|
Machine Translation (HP)
|
100% |
721
12.4 IPS |
|
Machine Translation (Q)
|
50% |
457
16.2 IPS |