Upload Date | June 15 2025 03:02 AM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT6769V/CZ |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A065F |
Model ID | samsung SM-A065F |
Motherboard | a06 |
CPU Information | |
---|---|
Name | ARM MT6769V/CZ |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 3.57 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
142
26.5 IPS |
|
Image Classification (HP)
|
100% |
133
24.8 IPS |
|
Image Classification (Q)
|
100% |
328
61.0 IPS |
|
Image Segmentation (SP)
|
100% |
160
2.60 IPS |
|
Image Segmentation (HP)
|
100% |
175
2.84 IPS |
|
Image Segmentation (Q)
|
98% |
459
7.46 IPS |
|
Pose Estimation (SP)
|
100% |
678
0.79 IPS |
|
Pose Estimation (HP)
|
100% |
663
0.77 IPS |
|
Pose Estimation (Q)
|
84% |
713
0.85 IPS |
|
Object Detection (SP)
|
100% |
122
9.66 IPS |
|
Object Detection (HP)
|
100% |
129
10.2 IPS |
|
Object Detection (Q)
|
83% |
355
28.7 IPS |
|
Face Detection (SP)
|
100% |
345
4.10 IPS |
|
Face Detection (HP)
|
100% |
352
4.19 IPS |
|
Face Detection (Q)
|
95% |
700
8.36 IPS |
|
Depth Estimation (SP)
|
100% |
451
3.48 IPS |
|
Depth Estimation (HP)
|
99% |
458
3.53 IPS |
|
Depth Estimation (Q)
|
64% |
605
5.54 IPS |
|
Style Transfer (SP)
|
89% |
1149
1.49 IPS |
|
Style Transfer (HP)
|
89% |
1083
1.41 IPS |
|
Style Transfer (Q)
|
98% |
1650
2.13 IPS |
|
Image Super-Resolution (SP)
|
100% |
256
9.46 IPS |
|
Image Super-Resolution (HP)
|
100% |
228
8.42 IPS |
|
Image Super-Resolution (Q)
|
97% |
524
19.4 IPS |
|
Text Classification (SP)
|
100% |
93
124.8 IPS |
|
Text Classification (HP)
|
100% |
149
198.4 IPS |
|
Text Classification (Q)
|
88% |
153
206.4 IPS |
|
Machine Translation (SP)
|
100% |
172
2.96 IPS |
|
Machine Translation (HP)
|
100% |
150
2.58 IPS |
|
Machine Translation (Q)
|
50% |
94
3.33 IPS |