Upload Date | January 16 2025 11:01 AM |
Views | 9 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | VALE GmbH, Germany V12E LTE-8128 |
Model ID | VALE GmbH, Germany V12E LTE-8128 |
Motherboard | ums9230_6h10 |
Governor | uscfreq |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 1.82 GHz |
Cluster 1 | 6 Cores @ 1.82 GHz |
Cluster 2 | 2 Cores @ 1.95 GHz |
Memory Information | |
---|---|
Size | 7.58 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
86
15.9 IPS |
|
Image Classification (HP)
|
100% |
151
28.0 IPS |
|
Image Classification (Q)
|
99% |
123
22.9 IPS |
|
Image Segmentation (SP)
|
100% |
122
1.97 IPS |
|
Image Segmentation (HP)
|
100% |
189
3.07 IPS |
|
Image Segmentation (Q)
|
98% |
167
2.71 IPS |
|
Pose Estimation (SP)
|
100% |
531
0.62 IPS |
|
Pose Estimation (HP)
|
100% |
298
0.35 IPS |
|
Pose Estimation (Q)
|
96% |
491
0.58 IPS |
|
Object Detection (SP)
|
100% |
49
3.89 IPS |
|
Object Detection (HP)
|
100% |
49
3.90 IPS |
|
Object Detection (Q)
|
87% |
96
7.73 IPS |
|
Face Detection (SP)
|
100% |
317
3.77 IPS |
|
Face Detection (HP)
|
100% |
374
4.45 IPS |
|
Face Detection (Q)
|
97% |
236
2.81 IPS |
|
Depth Estimation (SP)
|
100% |
418
3.22 IPS |
|
Depth Estimation (HP)
|
98% |
326
2.52 IPS |
|
Depth Estimation (Q)
|
66% |
393
3.47 IPS |
|
Style Transfer (SP)
|
100% |
372
0.48 IPS |
|
Style Transfer (HP)
|
100% |
219
0.28 IPS |
|
Style Transfer (Q)
|
98% |
729
0.94 IPS |
|
Image Super-Resolution (SP)
|
100% |
240
8.87 IPS |
|
Image Super-Resolution (HP)
|
100% |
165
6.10 IPS |
|
Image Super-Resolution (Q)
|
97% |
243
9.01 IPS |
|
Text Classification (SP)
|
100% |
39
52.5 IPS |
|
Text Classification (HP)
|
100% |
71
94.5 IPS |
|
Text Classification (Q)
|
93% |
58
78.4 IPS |
|
Machine Translation (SP)
|
100% |
96
1.65 IPS |
|
Machine Translation (HP)
|
100% |
127
2.19 IPS |
|
Machine Translation (Q)
|
55% |
67
1.78 IPS |