User | M91 |
Upload Date | July 25 2025 03:10 AM |
Views | 8 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-A166W |
Model ID | samsung SM-A166W |
Motherboard | s5e8535 |
Governor | energy_aware |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 3.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
122
22.7 IPS |
|
Image Classification (HP)
|
100% |
122
22.7 IPS |
|
Image Classification (Q)
|
99% |
328
61.1 IPS |
|
Image Segmentation (SP)
|
100% |
168
2.72 IPS |
|
Image Segmentation (HP)
|
100% |
169
2.73 IPS |
|
Image Segmentation (Q)
|
98% |
372
6.05 IPS |
|
Pose Estimation (SP)
|
100% |
219
0.26 IPS |
|
Pose Estimation (HP)
|
100% |
198
0.23 IPS |
|
Pose Estimation (Q)
|
98% |
826
0.97 IPS |
|
Object Detection (SP)
|
100% |
118
9.38 IPS |
|
Object Detection (HP)
|
100% |
119
9.41 IPS |
|
Object Detection (Q)
|
87% |
327
26.3 IPS |
|
Face Detection (SP)
|
100% |
300
3.56 IPS |
|
Face Detection (HP)
|
100% |
302
3.59 IPS |
|
Face Detection (Q)
|
97% |
685
8.17 IPS |
|
Depth Estimation (SP)
|
100% |
255
1.97 IPS |
|
Depth Estimation (HP)
|
99% |
245
1.89 IPS |
|
Depth Estimation (Q)
|
64% |
593
5.38 IPS |
|
Style Transfer (SP)
|
100% |
109
0.14 IPS |
|
Style Transfer (HP)
|
100% |
253
0.32 IPS |
|
Style Transfer (Q)
|
98% |
1280
1.65 IPS |
|
Image Super-Resolution (SP)
|
100% |
135
4.98 IPS |
|
Image Super-Resolution (HP)
|
100% |
134
4.96 IPS |
|
Image Super-Resolution (Q)
|
97% |
455
16.8 IPS |
|
Text Classification (SP)
|
100% |
174
232.6 IPS |
|
Text Classification (HP)
|
100% |
176
234.6 IPS |
|
Text Classification (Q)
|
91% |
339
455.2 IPS |
|
Machine Translation (SP)
|
100% |
298
5.12 IPS |
|
Machine Translation (HP)
|
100% |
296
5.10 IPS |
|
Machine Translation (Q)
|
57% |
280
6.85 IPS |