Upload Date | September 17 2024 03:07 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Nothing A142 |
Model ID | Nothing A142 |
Motherboard | Pacman |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3405 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.80 GHz |
Memory Information | |
---|---|
Size | 11.16 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
529
98.3 IPS |
|
Image Classification (HP)
|
100% |
543
101.1 IPS |
|
Image Classification (Q)
|
100% |
925
172.1 IPS |
|
Image Segmentation (SP)
|
100% |
605
9.81 IPS |
|
Image Segmentation (HP)
|
100% |
604
9.79 IPS |
|
Image Segmentation (Q)
|
98% |
964
15.7 IPS |
|
Pose Estimation (SP)
|
100% |
1108
1.29 IPS |
|
Pose Estimation (HP)
|
100% |
1108
1.29 IPS |
|
Pose Estimation (Q)
|
84% |
2622
3.11 IPS |
|
Object Detection (SP)
|
98% |
520
41.4 IPS |
|
Object Detection (HP)
|
98% |
520
41.3 IPS |
|
Object Detection (Q)
|
83% |
854
69.0 IPS |
|
Face Detection (SP)
|
100% |
1042
12.4 IPS |
|
Face Detection (HP)
|
100% |
1020
12.1 IPS |
|
Face Detection (Q)
|
95% |
2019
24.1 IPS |
|
Depth Estimation (SP)
|
99% |
916
7.08 IPS |
|
Depth Estimation (HP)
|
99% |
1146
8.85 IPS |
|
Depth Estimation (Q)
|
64% |
2097
19.2 IPS |
|
Style Transfer (SP)
|
89% |
2624
3.41 IPS |
|
Style Transfer (HP)
|
89% |
2611
3.39 IPS |
|
Style Transfer (Q)
|
98% |
5821
7.51 IPS |
|
Image Super-Resolution (SP)
|
100% |
535
19.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
532
19.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
1383
51.3 IPS |
|
Text Classification (SP)
|
100% |
287
383.0 IPS |
|
Text Classification (HP)
|
99% |
288
384.0 IPS |
|
Text Classification (Q)
|
88% |
757
1.02 KIPS |
|
Machine Translation (SP)
|
100% |
730
12.6 IPS |
|
Machine Translation (HP)
|
100% |
730
12.6 IPS |
|
Machine Translation (Q)
|
50% |
379
13.5 IPS |