Upload Date | December 28 2024 10:42 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-G525N |
Model ID | samsung SM-G525N |
Motherboard | exynos850 |
Governor | energy_aware |
CPU Information | |
---|---|
Name | ARM ARMv8 |
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 | 3.57 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
132
24.6 IPS |
|
Image Classification (HP)
|
100% |
117
21.8 IPS |
|
Image Classification (Q)
|
100% |
172
31.9 IPS |
|
Image Segmentation (SP)
|
100% |
166
2.69 IPS |
|
Image Segmentation (HP)
|
100% |
175
2.84 IPS |
|
Image Segmentation (Q)
|
98% |
261
4.24 IPS |
|
Pose Estimation (SP)
|
100% |
632
0.74 IPS |
|
Pose Estimation (HP)
|
100% |
587
0.69 IPS |
|
Pose Estimation (Q)
|
84% |
438
0.52 IPS |
|
Object Detection (SP)
|
100% |
137
10.8 IPS |
|
Object Detection (HP)
|
100% |
133
10.6 IPS |
|
Object Detection (Q)
|
83% |
171
13.8 IPS |
|
Face Detection (SP)
|
100% |
363
4.32 IPS |
|
Face Detection (HP)
|
100% |
334
3.97 IPS |
|
Face Detection (Q)
|
95% |
452
5.39 IPS |
|
Depth Estimation (SP)
|
100% |
438
3.38 IPS |
|
Depth Estimation (HP)
|
99% |
384
2.96 IPS |
|
Depth Estimation (Q)
|
64% |
435
3.98 IPS |
|
Style Transfer (SP)
|
89% |
1299
1.69 IPS |
|
Style Transfer (HP)
|
89% |
1311
1.70 IPS |
|
Style Transfer (Q)
|
98% |
1224
1.58 IPS |
|
Image Super-Resolution (SP)
|
100% |
246
9.07 IPS |
|
Image Super-Resolution (HP)
|
100% |
246
9.07 IPS |
|
Image Super-Resolution (Q)
|
97% |
251
9.31 IPS |
|
Text Classification (SP)
|
100% |
119
158.4 IPS |
|
Text Classification (HP)
|
100% |
118
157.3 IPS |
|
Text Classification (Q)
|
88% |
129
173.8 IPS |
|
Machine Translation (SP)
|
100% |
192
3.32 IPS |
|
Machine Translation (HP)
|
100% |
189
3.26 IPS |
|
Machine Translation (Q)
|
50% |
79
2.79 IPS |