Upload Date | April 13 2025 02:11 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S936B |
Model ID | samsung SM-S936B |
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% |
1971
366.6 IPS |
|
Image Classification (HP)
|
100% |
2098
390.1 IPS |
|
Image Classification (Q)
|
100% |
4415
821.0 IPS |
|
Image Segmentation (SP)
|
100% |
2501
40.5 IPS |
|
Image Segmentation (HP)
|
100% |
2409
39.1 IPS |
|
Image Segmentation (Q)
|
98% |
5315
86.4 IPS |
|
Pose Estimation (SP)
|
100% |
5481
6.40 IPS |
|
Pose Estimation (HP)
|
100% |
5454
6.36 IPS |
|
Pose Estimation (Q)
|
84% |
13832
16.4 IPS |
|
Object Detection (SP)
|
98% |
1718
136.7 IPS |
|
Object Detection (HP)
|
98% |
1732
137.9 IPS |
|
Object Detection (Q)
|
83% |
3981
321.6 IPS |
|
Face Detection (SP)
|
100% |
4542
54.0 IPS |
|
Face Detection (HP)
|
100% |
4471
53.1 IPS |
|
Face Detection (Q)
|
95% |
9678
115.5 IPS |
|
Depth Estimation (SP)
|
99% |
4770
36.9 IPS |
|
Depth Estimation (HP)
|
99% |
4664
36.0 IPS |
|
Depth Estimation (Q)
|
64% |
10694
98.0 IPS |
|
Style Transfer (SP)
|
89% |
11795
15.3 IPS |
|
Style Transfer (HP)
|
89% |
11528
15.0 IPS |
|
Style Transfer (Q)
|
98% |
25421
32.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
2421
89.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
2446
90.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
6352
235.4 IPS |
|
Text Classification (SP)
|
100% |
997
1.33 KIPS |
|
Text Classification (HP)
|
99% |
960
1.28 KIPS |
|
Text Classification (Q)
|
88% |
1028
1.39 KIPS |
|
Machine Translation (SP)
|
100% |
1391
24.0 IPS |
|
Machine Translation (HP)
|
100% |
1411
24.3 IPS |
|
Machine Translation (Q)
|
50% |
566
20.1 IPS |