Upload Date | October 09 2024 02:43 PM |
Views | 7 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Samsung Exynos 9611 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Samsung Galaxy Tab S6 Lite |
Model ID | samsung SM-P610 |
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 | 3.62 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
63
11.8 IPS |
|
Image Classification (HP)
|
100% |
117
21.8 IPS |
|
Image Classification (Q)
|
99% |
122
22.7 IPS |
|
Image Segmentation (SP)
|
100% |
120
1.94 IPS |
|
Image Segmentation (HP)
|
100% |
157
2.55 IPS |
|
Image Segmentation (Q)
|
98% |
154
2.50 IPS |
|
Pose Estimation (SP)
|
100% |
81
0.09 IPS |
|
Pose Estimation (HP)
|
100% |
109
0.13 IPS |
|
Pose Estimation (Q)
|
96% |
109
0.13 IPS |
|
Object Detection (SP)
|
100% |
86
6.85 IPS |
|
Object Detection (HP)
|
100% |
152
12.0 IPS |
|
Object Detection (Q)
|
83% |
146
11.8 IPS |
|
Face Detection (SP)
|
100% |
346
4.12 IPS |
|
Face Detection (HP)
|
100% |
461
5.47 IPS |
|
Face Detection (Q)
|
97% |
433
5.16 IPS |
|
Depth Estimation (SP)
|
100% |
178
1.37 IPS |
|
Depth Estimation (HP)
|
99% |
249
1.92 IPS |
|
Depth Estimation (Q)
|
62% |
202
1.91 IPS |
|
Style Transfer (SP)
|
100% |
327
0.42 IPS |
|
Style Transfer (HP)
|
100% |
486
0.63 IPS |
|
Style Transfer (Q)
|
98% |
546
0.70 IPS |
|
Image Super-Resolution (SP)
|
100% |
117
4.33 IPS |
|
Image Super-Resolution (HP)
|
100% |
178
6.56 IPS |
|
Image Super-Resolution (Q)
|
97% |
175
6.47 IPS |
|
Text Classification (SP)
|
100% |
66
88.2 IPS |
|
Text Classification (HP)
|
100% |
67
88.8 IPS |
|
Text Classification (Q)
|
91% |
87
116.4 IPS |
|
Machine Translation (SP)
|
100% |
117
2.01 IPS |
|
Machine Translation (HP)
|
100% |
104
1.79 IPS |
|
Machine Translation (Q)
|
57% |
88
2.15 IPS |