Upload Date | September 18 2024 01:14 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Samsung Exynos 9611 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Tab S6 Lite |
Model ID | samsung SM-P615 |
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 | 3.49 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
98
18.3 IPS |
|
Image Classification (HP)
|
100% |
118
22.0 IPS |
|
Image Classification (Q)
|
100% |
223
41.4 IPS |
|
Image Segmentation (SP)
|
100% |
169
2.74 IPS |
|
Image Segmentation (HP)
|
100% |
170
2.75 IPS |
|
Image Segmentation (Q)
|
98% |
306
4.97 IPS |
|
Pose Estimation (SP)
|
100% |
636
0.74 IPS |
|
Pose Estimation (HP)
|
100% |
606
0.71 IPS |
|
Pose Estimation (Q)
|
84% |
485
0.58 IPS |
|
Object Detection (SP)
|
100% |
116
9.19 IPS |
|
Object Detection (HP)
|
100% |
116
9.21 IPS |
|
Object Detection (Q)
|
83% |
212
17.1 IPS |
|
Face Detection (SP)
|
100% |
372
4.41 IPS |
|
Face Detection (HP)
|
100% |
371
4.41 IPS |
|
Face Detection (Q)
|
95% |
516
6.16 IPS |
|
Depth Estimation (SP)
|
100% |
486
3.75 IPS |
|
Depth Estimation (HP)
|
99% |
480
3.70 IPS |
|
Depth Estimation (Q)
|
64% |
506
4.63 IPS |
|
Style Transfer (SP)
|
89% |
1036
1.34 IPS |
|
Style Transfer (HP)
|
89% |
1036
1.35 IPS |
|
Style Transfer (Q)
|
98% |
1352
1.74 IPS |
|
Image Super-Resolution (SP)
|
100% |
263
9.72 IPS |
|
Image Super-Resolution (HP)
|
100% |
267
9.87 IPS |
|
Image Super-Resolution (Q)
|
97% |
283
10.5 IPS |
|
Text Classification (SP)
|
100% |
129
172.4 IPS |
|
Text Classification (HP)
|
100% |
128
170.7 IPS |
|
Text Classification (Q)
|
88% |
186
251.3 IPS |
|
Machine Translation (SP)
|
100% |
224
3.86 IPS |
|
Machine Translation (HP)
|
100% |
222
3.83 IPS |
|
Machine Translation (Q)
|
50% |
124
4.41 IPS |