User | benched |
Upload Date | October 08 2024 04:55 PM |
Views | 7 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM Samsung |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A047F |
Model ID | samsung SM-A047F |
Motherboard | exynos850 |
Governor | energy_step |
CPU Information | |
---|---|
Name | ARM Samsung |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3333 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 8 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 2.64 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
30
5.52 IPS |
|
Image Classification (HP)
|
100% |
40
7.45 IPS |
|
Image Classification (Q)
|
99% |
39
7.30 IPS |
|
Image Segmentation (SP)
|
100% |
41
0.66 IPS |
|
Image Segmentation (HP)
|
100% |
53
0.86 IPS |
|
Image Segmentation (Q)
|
98% |
53
0.86 IPS |
|
Pose Estimation (SP)
|
100% |
31
0.04 IPS |
|
Pose Estimation (HP)
|
100% |
42
0.05 IPS |
|
Pose Estimation (Q)
|
96% |
42
0.05 IPS |
|
Object Detection (SP)
|
100% |
37
2.95 IPS |
|
Object Detection (HP)
|
100% |
54
4.25 IPS |
|
Object Detection (Q)
|
83% |
52
4.21 IPS |
|
Face Detection (SP)
|
100% |
148
1.76 IPS |
|
Face Detection (HP)
|
100% |
205
2.44 IPS |
|
Face Detection (Q)
|
97% |
195
2.32 IPS |
|
Depth Estimation (SP)
|
100% |
70
0.54 IPS |
|
Depth Estimation (HP)
|
99% |
91
0.70 IPS |
|
Depth Estimation (Q)
|
62% |
73
0.69 IPS |
|
Style Transfer (SP)
|
100% |
147
0.19 IPS |
|
Style Transfer (HP)
|
100% |
193
0.25 IPS |
|
Style Transfer (Q)
|
98% |
192
0.25 IPS |
|
Image Super-Resolution (SP)
|
100% |
37
1.38 IPS |
|
Image Super-Resolution (HP)
|
100% |
53
1.96 IPS |
|
Image Super-Resolution (Q)
|
97% |
53
1.96 IPS |
|
Text Classification (SP)
|
100% |
45
59.8 IPS |
|
Text Classification (HP)
|
100% |
45
60.1 IPS |
|
Text Classification (Q)
|
91% |
46
61.6 IPS |
|
Machine Translation (SP)
|
100% |
80
1.38 IPS |
|
Machine Translation (HP)
|
100% |
81
1.40 IPS |
|
Machine Translation (Q)
|
57% |
49
1.19 IPS |