Upload Date | September 11 2025 02:03 AM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-A165M |
Model ID | samsung SM-A165M |
Motherboard | a16 |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.20 GHz |
Memory Information | |
---|---|
Size | 3.54 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
167
31.0 IPS |
|
Image Classification (HP)
|
100% |
418
77.8 IPS |
|
Image Classification (Q)
|
97% |
302
56.3 IPS |
|
Image Segmentation (SP)
|
100% |
287
4.65 IPS |
|
Image Segmentation (HP)
|
100% |
572
9.27 IPS |
|
Image Segmentation (Q)
|
98% |
600
9.75 IPS |
|
Pose Estimation (SP)
|
100% |
1107
1.29 IPS |
|
Pose Estimation (HP)
|
100% |
1978
2.31 IPS |
|
Pose Estimation (Q)
|
95% |
2040
2.39 IPS |
|
Object Detection (SP)
|
100% |
151
12.0 IPS |
|
Object Detection (HP)
|
99% |
281
22.3 IPS |
|
Object Detection (Q)
|
83% |
357
28.8 IPS |
|
Face Detection (SP)
|
100% |
715
8.49 IPS |
|
Face Detection (HP)
|
100% |
1601
19.0 IPS |
|
Face Detection (Q)
|
96% |
1407
16.8 IPS |
|
Depth Estimation (SP)
|
100% |
800
6.17 IPS |
|
Depth Estimation (HP)
|
98% |
1665
12.9 IPS |
|
Depth Estimation (Q)
|
62% |
1212
11.5 IPS |
|
Style Transfer (SP)
|
100% |
1886
2.42 IPS |
|
Style Transfer (HP)
|
100% |
4115
5.29 IPS |
|
Style Transfer (Q)
|
98% |
3916
5.05 IPS |
|
Image Super-Resolution (SP)
|
100% |
459
17.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
795
29.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
787
29.2 IPS |
|
Text Classification (SP)
|
35% |
13
114.6 IPS |
|
Text Classification (HP)
|
29% |
9
150.4 IPS |
|
Text Classification (Q)
|
32% |
6
77.6 IPS |
|
Machine Translation (SP)
|
100% |
273
4.71 IPS |
|
Machine Translation (HP)
|
100% |
241
4.15 IPS |
|
Machine Translation (Q)
|
43% |
88
5.10 IPS |