User | leow149 |
Upload Date | January 05 2025 08:36 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Nothing A142P |
Model ID | Nothing A142P |
Motherboard | PacmanPro |
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 @ 3.00 GHz |
Memory Information | |
---|---|
Size | 11.16 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
461
85.8 IPS |
|
Image Classification (HP)
|
100% |
1524
283.4 IPS |
|
Image Classification (Q)
|
99% |
4422
824.9 IPS |
|
Image Segmentation (SP)
|
100% |
347
5.63 IPS |
|
Image Segmentation (HP)
|
100% |
1575
25.5 IPS |
|
Image Segmentation (Q)
|
98% |
1156
18.8 IPS |
|
Pose Estimation (SP)
|
100% |
2552
2.98 IPS |
|
Pose Estimation (HP)
|
100% |
6974
8.14 IPS |
|
Pose Estimation (Q)
|
95% |
28269
33.1 IPS |
|
Object Detection (SP)
|
100% |
331
26.2 IPS |
|
Object Detection (HP)
|
100% |
1398
110.9 IPS |
|
Object Detection (Q)
|
86% |
2211
177.8 IPS |
|
Face Detection (SP)
|
28% |
76
14.1 IPS |
|
Face Detection (HP)
|
100% |
3544
42.1 IPS |
|
Face Detection (Q)
|
97% |
7028
83.8 IPS |
|
Depth Estimation (SP)
|
100% |
624
4.81 IPS |
|
Depth Estimation (HP)
|
99% |
7128
54.9 IPS |
|
Depth Estimation (Q)
|
62% |
14748
140.0 IPS |
|
Style Transfer (SP)
|
100% |
1226
1.58 IPS |
|
Style Transfer (HP)
|
100% |
467
0.60 IPS |
|
Style Transfer (Q)
|
30% |
379
5.71 IPS |
|
Image Super-Resolution (SP)
|
100% |
862
31.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
4320
159.5 IPS |
|
Image Super-Resolution (Q)
|
41% |
2885
420.1 IPS |
|
Text Classification (SP)
|
100% |
115
153.0 IPS |
|
Text Classification (HP)
|
100% |
177
235.8 IPS |
|
Text Classification (Q)
|
93% |
811
1.09 KIPS |
|
Machine Translation (SP)
|
100% |
234
4.03 IPS |
|
Machine Translation (HP)
|
100% |
283
4.88 IPS |
|
Machine Translation (Q)
|
60% |
250
5.63 IPS |