Upload Date | April 30 2025 05:13 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 8 Gen 2 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Samsung Galaxy S23 Plus |
Model ID | samsung SM-S916U |
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% |
983
182.7 IPS |
|
Image Classification (HP)
|
100% |
706
131.2 IPS |
|
Image Classification (Q)
|
100% |
1485
276.1 IPS |
|
Image Segmentation (SP)
|
100% |
666
10.8 IPS |
|
Image Segmentation (HP)
|
100% |
479
7.77 IPS |
|
Image Segmentation (Q)
|
98% |
1735
28.2 IPS |
|
Pose Estimation (SP)
|
100% |
1748
2.04 IPS |
|
Pose Estimation (HP)
|
100% |
1236
1.44 IPS |
|
Pose Estimation (Q)
|
84% |
2931
3.48 IPS |
|
Object Detection (SP)
|
98% |
510
40.6 IPS |
|
Object Detection (HP)
|
98% |
568
45.2 IPS |
|
Object Detection (Q)
|
83% |
1051
84.9 IPS |
|
Face Detection (SP)
|
100% |
1001
11.9 IPS |
|
Face Detection (HP)
|
100% |
1006
12.0 IPS |
|
Face Detection (Q)
|
95% |
1603
19.1 IPS |
|
Depth Estimation (SP)
|
99% |
1266
9.79 IPS |
|
Depth Estimation (HP)
|
99% |
1119
8.65 IPS |
|
Depth Estimation (Q)
|
64% |
2285
20.9 IPS |
|
Style Transfer (SP)
|
89% |
2996
3.89 IPS |
|
Style Transfer (HP)
|
89% |
2972
3.86 IPS |
|
Style Transfer (Q)
|
98% |
5299
6.83 IPS |
|
Image Super-Resolution (SP)
|
100% |
772
28.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
671
24.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
1486
55.0 IPS |
|
Text Classification (SP)
|
100% |
388
518.2 IPS |
|
Text Classification (HP)
|
99% |
235
313.6 IPS |
|
Text Classification (Q)
|
88% |
443
597.3 IPS |
|
Machine Translation (SP)
|
100% |
864
14.9 IPS |
|
Machine Translation (HP)
|
100% |
630
10.9 IPS |
|
Machine Translation (Q)
|
50% |
339
12.0 IPS |