Upload Date | September 09 2025 05:56 AM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARMv8 |
System Information | |
---|---|
Operating System | Android 12 |
Model | samsung SM-G975F |
Model ID | samsung SM-G975F |
Motherboard | exynos9820 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 83 architecture 8 variant 1 part 3 revision 0 |
Base Frequency | 1.95 GHz |
Cluster 1 | 4 Cores @ 1.95 GHz |
Cluster 2 | 2 Cores @ 2.31 GHz |
Cluster 3 | 2 Cores @ 2.73 GHz |
Memory Information | |
---|---|
Size | 7.25 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
443
82.5 IPS |
|
Image Classification (HP)
|
100% |
671
124.8 IPS |
|
Image Classification (Q)
|
97% |
621
115.9 IPS |
|
Image Segmentation (SP)
|
100% |
684
11.1 IPS |
|
Image Segmentation (HP)
|
100% |
1261
20.4 IPS |
|
Image Segmentation (Q)
|
98% |
1015
16.5 IPS |
|
Pose Estimation (SP)
|
100% |
2790
3.26 IPS |
|
Pose Estimation (HP)
|
100% |
3674
4.29 IPS |
|
Pose Estimation (Q)
|
95% |
3589
4.21 IPS |
|
Object Detection (SP)
|
100% |
232
18.4 IPS |
|
Object Detection (HP)
|
99% |
431
34.2 IPS |
|
Object Detection (Q)
|
83% |
407
32.9 IPS |
|
Face Detection (SP)
|
100% |
1008
12.0 IPS |
|
Face Detection (HP)
|
100% |
1773
21.1 IPS |
|
Face Detection (Q)
|
96% |
1506
18.0 IPS |
|
Depth Estimation (SP)
|
100% |
1001
7.71 IPS |
|
Depth Estimation (HP)
|
98% |
1931
14.9 IPS |
|
Depth Estimation (Q)
|
62% |
1352
12.8 IPS |
|
Style Transfer (SP)
|
100% |
2803
3.60 IPS |
|
Style Transfer (HP)
|
100% |
5481
7.05 IPS |
|
Style Transfer (Q)
|
98% |
5487
7.08 IPS |
|
Image Super-Resolution (SP)
|
100% |
658
24.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
1069
39.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
1080
40.0 IPS |
|
Text Classification (SP)
|
35% |
13
115.0 IPS |
|
Text Classification (HP)
|
29% |
9
160.2 IPS |
|
Text Classification (Q)
|
29% |
9
153.8 IPS |
|
Machine Translation (SP)
|
100% |
249
4.29 IPS |
|
Machine Translation (HP)
|
100% |
398
6.86 IPS |
|
Machine Translation (Q)
|
43% |
95
5.55 IPS |