Upload Date | August 20 2025 07:45 AM |
Views | 3 |
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% |
422
78.4 IPS |
|
Image Classification (HP)
|
100% |
21258
3.95 KIPS |
|
Image Classification (Q)
|
97% |
49043
9.15 KIPS |
|
Image Segmentation (SP)
|
100% |
553
8.96 IPS |
|
Image Segmentation (HP)
|
100% |
13264
215.0 IPS |
|
Image Segmentation (Q)
|
98% |
38722
629.6 IPS |
|
Pose Estimation (SP)
|
100% |
401
0.47 IPS |
|
Pose Estimation (HP)
|
100% |
122251
142.6 IPS |
|
Pose Estimation (Q)
|
98% |
473590
554.3 IPS |
|
Object Detection (SP)
|
100% |
210
16.6 IPS |
|
Object Detection (HP)
|
100% |
17878
1.42 KIPS |
|
Object Detection (Q)
|
85% |
20450
1.65 KIPS |
|
Face Detection (SP)
|
100% |
568
6.75 IPS |
|
Face Detection (HP)
|
100% |
38003
451.6 IPS |
|
Face Detection (Q)
|
97% |
119727
1.43 KIPS |
|
Depth Estimation (SP)
|
100% |
494
3.80 IPS |
|
Depth Estimation (HP)
|
99% |
80202
617.9 IPS |
|
Depth Estimation (Q)
|
63% |
134127
1.24 KIPS |
|
Style Transfer (SP)
|
100% |
901
1.16 IPS |
|
Style Transfer (HP)
|
98% |
98233
126.7 IPS |
|
Style Transfer (Q)
|
98% |
487840
629.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
244
9.01 IPS |
|
Image Super-Resolution (HP)
|
100% |
51911
1.92 KIPS |
|
Image Super-Resolution (Q)
|
97% |
125718
4.66 KIPS |
|
Text Classification (SP)
|
100% |
315
420.9 IPS |
|
Text Classification (HP)
|
100% |
3857
5.15 KIPS |
|
Text Classification (Q)
|
93% |
7740
10.4 KIPS |
|
Machine Translation (SP)
|
100% |
556
9.57 IPS |
|
Machine Translation (HP)
|
100% |
4208
72.5 IPS |
|
Machine Translation (Q)
|
56% |
2787
71.8 IPS |