Upload Date | February 01 2025 11:55 PM |
Views | 10 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S938B |
Model ID | samsung SM-S938B |
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% |
464
86.3 IPS |
|
Image Classification (HP)
|
100% |
21952
4.08 KIPS |
|
Image Classification (Q)
|
97% |
49488
9.24 KIPS |
|
Image Segmentation (SP)
|
100% |
599
9.70 IPS |
|
Image Segmentation (HP)
|
100% |
13752
222.9 IPS |
|
Image Segmentation (Q)
|
98% |
42315
688.1 IPS |
|
Pose Estimation (SP)
|
100% |
774
0.90 IPS |
|
Pose Estimation (HP)
|
100% |
123351
143.9 IPS |
|
Pose Estimation (Q)
|
98% |
480900
562.9 IPS |
|
Object Detection (SP)
|
100% |
427
33.8 IPS |
|
Object Detection (HP)
|
100% |
19740
1.57 KIPS |
|
Object Detection (Q)
|
85% |
23074
1.86 KIPS |
|
Face Detection (SP)
|
100% |
1088
12.9 IPS |
|
Face Detection (HP)
|
100% |
44587
529.8 IPS |
|
Face Detection (Q)
|
97% |
162306
1.94 KIPS |
|
Depth Estimation (SP)
|
100% |
942
7.26 IPS |
|
Depth Estimation (HP)
|
99% |
85043
655.2 IPS |
|
Depth Estimation (Q)
|
63% |
147813
1.37 KIPS |
|
Style Transfer (SP)
|
100% |
1574
2.02 IPS |
|
Style Transfer (HP)
|
98% |
98916
127.6 IPS |
|
Style Transfer (Q)
|
98% |
496477
640.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
497
18.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
55576
2.05 KIPS |
|
Image Super-Resolution (Q)
|
97% |
135649
5.03 KIPS |
|
Text Classification (SP)
|
100% |
656
875.9 IPS |
|
Text Classification (HP)
|
100% |
3925
5.24 KIPS |
|
Text Classification (Q)
|
93% |
8082
10.8 KIPS |
|
Machine Translation (SP)
|
100% |
1057
18.2 IPS |
|
Machine Translation (HP)
|
100% |
4884
84.1 IPS |
|
Machine Translation (Q)
|
56% |
3262
84.0 IPS |