User | Asgardian456 |
Upload Date | July 01 2025 11:54 AM |
Views | 9 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Samsung Exynos 9611 |
System Information | |
---|---|
Operating System | Android 12 |
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)
|
100% |
33
6.19 IPS |
|
Image Classification (HP)
|
100% |
34
6.25 IPS |
|
Image Classification (Q)
|
99% |
57
10.6 IPS |
|
Image Segmentation (SP)
|
100% |
45
0.73 IPS |
|
Image Segmentation (HP)
|
100% |
45
0.74 IPS |
|
Image Segmentation (Q)
|
98% |
63
1.03 IPS |
|
Pose Estimation (SP)
|
100% |
66
0.08 IPS |
|
Pose Estimation (HP)
|
100% |
66
0.08 IPS |
|
Pose Estimation (Q)
|
98% |
170
0.20 IPS |
|
Object Detection (SP)
|
100% |
34
2.67 IPS |
|
Object Detection (HP)
|
100% |
34
2.69 IPS |
|
Object Detection (Q)
|
87% |
59
4.76 IPS |
|
Face Detection (SP)
|
100% |
88
1.05 IPS |
|
Face Detection (HP)
|
100% |
89
1.06 IPS |
|
Face Detection (Q)
|
97% |
151
1.80 IPS |
|
Depth Estimation (SP)
|
100% |
107
0.82 IPS |
|
Depth Estimation (HP)
|
99% |
96
0.74 IPS |
|
Depth Estimation (Q)
|
64% |
116
1.06 IPS |
|
Style Transfer (SP)
|
100% |
149
0.19 IPS |
|
Style Transfer (HP)
|
100% |
197
0.25 IPS |
|
Style Transfer (Q)
|
98% |
340
0.44 IPS |
|
Image Super-Resolution (SP)
|
100% |
40
1.46 IPS |
|
Image Super-Resolution (HP)
|
100% |
39
1.46 IPS |
|
Image Super-Resolution (Q)
|
97% |
82
3.04 IPS |
|
Text Classification (SP)
|
100% |
63
84.2 IPS |
|
Text Classification (HP)
|
100% |
66
88.3 IPS |
|
Text Classification (Q)
|
91% |
87
116.6 IPS |
|
Machine Translation (SP)
|
100% |
115
1.97 IPS |
|
Machine Translation (HP)
|
100% |
107
1.85 IPS |
|
Machine Translation (Q)
|
57% |
64
1.56 IPS |