User | naaajsboy |
Upload Date | September 02 2024 10:46 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
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 | 7.28 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
416
77.4 IPS |
|
Image Classification (HP)
|
100% |
1536
285.7 IPS |
|
Image Classification (Q)
|
97% |
4604
859.1 IPS |
|
Image Segmentation (SP)
|
100% |
560
9.08 IPS |
|
Image Segmentation (HP)
|
100% |
1656
26.8 IPS |
|
Image Segmentation (Q)
|
98% |
2075
33.7 IPS |
|
Pose Estimation (SP)
|
100% |
2651
3.09 IPS |
|
Pose Estimation (HP)
|
100% |
6669
7.78 IPS |
|
Pose Estimation (Q)
|
95% |
26979
31.6 IPS |
|
Object Detection (SP)
|
100% |
306
24.3 IPS |
|
Object Detection (HP)
|
100% |
1400
111.1 IPS |
|
Object Detection (Q)
|
88% |
2210
177.1 IPS |
|
Face Detection (SP)
|
100% |
1297
15.4 IPS |
|
Face Detection (HP)
|
100% |
3744
44.5 IPS |
|
Face Detection (Q)
|
97% |
9229
110.1 IPS |
|
Depth Estimation (SP)
|
100% |
404
3.11 IPS |
|
Depth Estimation (HP)
|
99% |
6911
53.2 IPS |
|
Depth Estimation (Q)
|
78% |
17166
136.9 IPS |
|
Style Transfer (SP)
|
100% |
1666
2.14 IPS |
|
Style Transfer (HP)
|
100% |
322
0.41 IPS |
|
Style Transfer (Q)
|
30% |
387
5.83 IPS |
|
Image Super-Resolution (SP)
|
100% |
922
34.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
4144
153.0 IPS |
|
Image Super-Resolution (Q)
|
41% |
3041
442.9 IPS |
|
Text Classification (SP)
|
100% |
73
97.8 IPS |
|
Text Classification (HP)
|
100% |
115
153.5 IPS |
|
Text Classification (Q)
|
93% |
1320
1.77 KIPS |
|
Machine Translation (SP)
|
100% |
183
3.16 IPS |
|
Machine Translation (HP)
|
100% |
191
3.28 IPS |
|
Machine Translation (Q)
|
53% |
186
5.33 IPS |