Upload Date | September 20 2025 08:45 AM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 8 Elite |
System Information | |
---|---|
Operating System | Android 15 |
Model | Samsung Galaxy S25+ |
Model ID | samsung SM-S936N |
Motherboard | sun |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 3 part 1 revision 4 |
Base Frequency | 3.53 GHz |
Cluster 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.47 GHz |
Memory Information | |
---|---|
Size | 10.86 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1962
364.9 IPS |
|
Image Classification (HP)
|
100% |
1952
363.0 IPS |
|
Image Classification (Q)
|
100% |
4537
843.8 IPS |
|
Image Segmentation (SP)
|
100% |
2502
40.6 IPS |
|
Image Segmentation (HP)
|
100% |
2451
39.7 IPS |
|
Image Segmentation (Q)
|
98% |
5514
89.7 IPS |
|
Pose Estimation (SP)
|
100% |
5788
6.75 IPS |
|
Pose Estimation (HP)
|
100% |
5414
6.32 IPS |
|
Pose Estimation (Q)
|
84% |
13230
15.7 IPS |
|
Object Detection (SP)
|
98% |
1788
142.3 IPS |
|
Object Detection (HP)
|
98% |
1633
130.0 IPS |
|
Object Detection (Q)
|
83% |
3779
305.2 IPS |
|
Face Detection (SP)
|
100% |
4281
50.9 IPS |
|
Face Detection (HP)
|
100% |
4396
52.2 IPS |
|
Face Detection (Q)
|
95% |
9581
114.4 IPS |
|
Depth Estimation (SP)
|
99% |
4698
36.3 IPS |
|
Depth Estimation (HP)
|
99% |
4677
36.1 IPS |
|
Depth Estimation (Q)
|
64% |
10796
98.9 IPS |
|
Style Transfer (SP)
|
89% |
11481
14.9 IPS |
|
Style Transfer (HP)
|
89% |
10975
14.2 IPS |
|
Style Transfer (Q)
|
98% |
25474
32.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
2290
84.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
2337
86.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
6567
243.3 IPS |
|
Text Classification (SP)
|
100% |
967
1.29 KIPS |
|
Text Classification (HP)
|
99% |
941
1.26 KIPS |
|
Text Classification (Q)
|
88% |
1033
1.39 KIPS |
|
Machine Translation (SP)
|
100% |
1400
24.1 IPS |
|
Machine Translation (HP)
|
100% |
1379
23.8 IPS |
|
Machine Translation (Q)
|
50% |
550
19.5 IPS |