User | mamiyoshi |
Upload Date | April 28 2025 02:13 PM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S938Q |
Model ID | samsung SM-S938Q |
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% |
448
83.2 IPS |
|
Image Classification (HP)
|
100% |
20850
3.88 KIPS |
|
Image Classification (Q)
|
97% |
49048
9.15 KIPS |
|
Image Segmentation (SP)
|
100% |
551
8.93 IPS |
|
Image Segmentation (HP)
|
100% |
13524
219.2 IPS |
|
Image Segmentation (Q)
|
98% |
42063
684.0 IPS |
|
Pose Estimation (SP)
|
100% |
644
0.75 IPS |
|
Pose Estimation (HP)
|
100% |
123283
143.9 IPS |
|
Pose Estimation (Q)
|
98% |
476616
557.9 IPS |
|
Object Detection (SP)
|
100% |
364
28.9 IPS |
|
Object Detection (HP)
|
100% |
19482
1.55 KIPS |
|
Object Detection (Q)
|
85% |
22500
1.81 KIPS |
|
Face Detection (SP)
|
100% |
883
10.5 IPS |
|
Face Detection (HP)
|
100% |
43006
511.0 IPS |
|
Face Detection (Q)
|
97% |
150965
1.80 KIPS |
|
Depth Estimation (SP)
|
100% |
818
6.30 IPS |
|
Depth Estimation (HP)
|
99% |
84170
648.5 IPS |
|
Depth Estimation (Q)
|
63% |
144463
1.34 KIPS |
|
Style Transfer (SP)
|
100% |
1408
1.81 IPS |
|
Style Transfer (HP)
|
98% |
98776
127.4 IPS |
|
Style Transfer (Q)
|
98% |
490599
632.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
340
12.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
53089
1.96 KIPS |
|
Image Super-Resolution (Q)
|
97% |
134619
4.99 KIPS |
|
Text Classification (SP)
|
100% |
498
664.1 IPS |
|
Text Classification (HP)
|
100% |
3903
5.21 KIPS |
|
Text Classification (Q)
|
93% |
7955
10.7 KIPS |
|
Machine Translation (SP)
|
100% |
890
15.3 IPS |
|
Machine Translation (HP)
|
100% |
4735
81.6 IPS |
|
Machine Translation (Q)
|
56% |
3161
81.4 IPS |