User | Shayan_Q9 |
Upload Date | September 19 2025 05:46 AM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Samsung Exynos 9611 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Galaxy A51 |
Model ID | samsung SM-A515F |
Motherboard | exynos9611 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3337 revision 2 |
Base Frequency | 1.74 GHz |
Cluster 1 | 4 Cores @ 1.74 GHz |
Cluster 2 | 4 Cores @ 2.31 GHz |
Memory Information | |
---|---|
Size | 5.44 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
0% |
0
34.4 IPS |
|
Image Classification (HP)
|
100% |
324
60.3 IPS |
|
Image Classification (Q)
|
97% |
300
55.9 IPS |
|
Image Segmentation (SP)
|
73% |
250
4.32 IPS |
|
Image Segmentation (HP)
|
100% |
480
7.79 IPS |
|
Image Segmentation (Q)
|
98% |
437
7.11 IPS |
|
Pose Estimation (SP)
|
100% |
1076
1.26 IPS |
|
Pose Estimation (HP)
|
100% |
2147
2.51 IPS |
|
Pose Estimation (Q)
|
95% |
2099
2.46 IPS |
|
Object Detection (SP)
|
1% |
0
13.3 IPS |
|
Object Detection (HP)
|
99% |
311
24.6 IPS |
|
Object Detection (Q)
|
83% |
282
22.7 IPS |
|
Face Detection (SP)
|
0% |
0
7.51 IPS |
|
Face Detection (HP)
|
100% |
1119
13.3 IPS |
|
Face Detection (Q)
|
96% |
930
11.1 IPS |
|
Depth Estimation (SP)
|
1% |
2
5.23 IPS |
|
Depth Estimation (HP)
|
98% |
1242
9.59 IPS |
|
Depth Estimation (Q)
|
62% |
970
9.22 IPS |
|
Style Transfer (SP)
|
100% |
1417
1.82 IPS |
|
Style Transfer (HP)
|
100% |
2876
3.70 IPS |
|
Style Transfer (Q)
|
98% |
2826
3.64 IPS |
|
Image Super-Resolution (SP)
|
100% |
466
17.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
796
29.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
798
29.6 IPS |
|
Text Classification (SP)
|
35% |
13
122.7 IPS |
|
Text Classification (HP)
|
35% |
15
137.5 IPS |
|
Text Classification (Q)
|
32% |
11
136.9 IPS |
|
Machine Translation (SP)
|
100% |
207
3.57 IPS |
|
Machine Translation (HP)
|
100% |
247
4.25 IPS |
|
Machine Translation (Q)
|
43% |
59
3.44 IPS |