Upload Date | October 22 2025 06:40 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 8 Gen 2 |
System Information | |
---|---|
Operating System | Android 16 |
Model | Samsung Galaxy S23 Plus |
Model ID | samsung SM-S916W |
Motherboard | kalama |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
Base Frequency | 2.02 GHz |
Cluster 1 | 3 Cores @ 2.02 GHz |
Cluster 2 | 4 Cores @ 2.80 GHz |
Cluster 3 | 1 Core @ 3.36 GHz |
Memory Information | |
---|---|
Size | 6.91 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
936
174.1 IPS |
|
Image Classification (HP)
|
100% |
663
123.3 IPS |
|
Image Classification (Q)
|
100% |
1468
273.0 IPS |
|
Image Segmentation (SP)
|
100% |
656
10.6 IPS |
|
Image Segmentation (HP)
|
100% |
408
6.61 IPS |
|
Image Segmentation (Q)
|
98% |
1348
21.9 IPS |
|
Pose Estimation (SP)
|
100% |
1937
2.26 IPS |
|
Pose Estimation (HP)
|
100% |
1914
2.23 IPS |
|
Pose Estimation (Q)
|
84% |
3273
3.88 IPS |
|
Object Detection (SP)
|
98% |
378
30.1 IPS |
|
Object Detection (HP)
|
98% |
672
53.5 IPS |
|
Object Detection (Q)
|
83% |
1183
95.5 IPS |
|
Face Detection (SP)
|
100% |
1143
13.6 IPS |
|
Face Detection (HP)
|
100% |
1151
13.7 IPS |
|
Face Detection (Q)
|
95% |
2588
30.9 IPS |
|
Depth Estimation (SP)
|
99% |
1429
11.0 IPS |
|
Depth Estimation (HP)
|
99% |
1630
12.6 IPS |
|
Depth Estimation (Q)
|
64% |
2013
18.4 IPS |
|
Style Transfer (SP)
|
89% |
3470
4.50 IPS |
|
Style Transfer (HP)
|
89% |
2989
3.88 IPS |
|
Style Transfer (Q)
|
98% |
5536
7.14 IPS |
|
Image Super-Resolution (SP)
|
100% |
672
24.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
550
20.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
1168
43.3 IPS |
|
Text Classification (SP)
|
100% |
353
471.0 IPS |
|
Text Classification (HP)
|
99% |
253
338.0 IPS |
|
Text Classification (Q)
|
88% |
534
720.1 IPS |
|
Machine Translation (SP)
|
100% |
707
12.2 IPS |
|
Machine Translation (HP)
|
100% |
452
7.79 IPS |
|
Machine Translation (Q)
|
50% |
382
13.5 IPS |