Upload Date | August 21 2025 04:23 PM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | Qualcomm Snapdragon 8 Elite |
System Information | |
---|---|
Operating System | Android 15 |
Model | Samsung Galaxy S25 |
Model ID | samsung SM-S931B |
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% |
428
79.5 IPS |
|
Image Classification (HP)
|
100% |
20956
3.90 KIPS |
|
Image Classification (Q)
|
97% |
49264
9.19 KIPS |
|
Image Segmentation (SP)
|
100% |
533
8.65 IPS |
|
Image Segmentation (HP)
|
100% |
13788
223.5 IPS |
|
Image Segmentation (Q)
|
98% |
42126
685.0 IPS |
|
Pose Estimation (SP)
|
100% |
620
0.72 IPS |
|
Pose Estimation (HP)
|
100% |
123151
143.7 IPS |
|
Pose Estimation (Q)
|
98% |
478200
559.7 IPS |
|
Object Detection (SP)
|
100% |
341
27.1 IPS |
|
Object Detection (HP)
|
100% |
18963
1.50 KIPS |
|
Object Detection (Q)
|
85% |
22085
1.78 KIPS |
|
Face Detection (SP)
|
100% |
802
9.52 IPS |
|
Face Detection (HP)
|
100% |
35732
424.6 IPS |
|
Face Detection (Q)
|
97% |
111374
1.33 KIPS |
|
Depth Estimation (SP)
|
100% |
573
4.41 IPS |
|
Depth Estimation (HP)
|
99% |
83499
643.3 IPS |
|
Depth Estimation (Q)
|
63% |
142036
1.31 KIPS |
|
Style Transfer (SP)
|
100% |
1103
1.42 IPS |
|
Style Transfer (HP)
|
98% |
98348
126.8 IPS |
|
Style Transfer (Q)
|
98% |
489907
631.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
316
11.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
51971
1.92 KIPS |
|
Image Super-Resolution (Q)
|
97% |
125000
4.63 KIPS |
|
Text Classification (SP)
|
100% |
363
484.6 IPS |
|
Text Classification (HP)
|
100% |
3886
5.19 KIPS |
|
Text Classification (Q)
|
93% |
7818
10.5 KIPS |
|
Machine Translation (SP)
|
100% |
628
10.8 IPS |
|
Machine Translation (HP)
|
100% |
3984
68.6 IPS |
|
Machine Translation (Q)
|
56% |
2675
68.9 IPS |