User | mvl30 |
Upload Date | March 04 2025 04:17 AM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S931U |
Model ID | samsung SM-S931U |
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% |
198
36.9 IPS |
|
Image Classification (HP)
|
100% |
19785
3.68 KIPS |
|
Image Classification (Q)
|
97% |
45926
8.57 KIPS |
|
Image Segmentation (SP)
|
100% |
234
3.79 IPS |
|
Image Segmentation (HP)
|
100% |
12635
204.8 IPS |
|
Image Segmentation (Q)
|
98% |
38466
625.5 IPS |
|
Pose Estimation (SP)
|
100% |
338
0.39 IPS |
|
Pose Estimation (HP)
|
100% |
122094
142.5 IPS |
|
Pose Estimation (Q)
|
98% |
473628
554.4 IPS |
|
Object Detection (SP)
|
100% |
174
13.8 IPS |
|
Object Detection (HP)
|
100% |
16028
1.27 KIPS |
|
Object Detection (Q)
|
85% |
19044
1.53 KIPS |
|
Face Detection (SP)
|
100% |
434
5.16 IPS |
|
Face Detection (HP)
|
100% |
35181
418.0 IPS |
|
Face Detection (Q)
|
97% |
120934
1.44 KIPS |
|
Depth Estimation (SP)
|
100% |
409
3.15 IPS |
|
Depth Estimation (HP)
|
99% |
80334
618.9 IPS |
|
Depth Estimation (Q)
|
63% |
134443
1.24 KIPS |
|
Style Transfer (SP)
|
100% |
750
0.96 IPS |
|
Style Transfer (HP)
|
98% |
98261
126.7 IPS |
|
Style Transfer (Q)
|
98% |
489229
630.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
205
7.57 IPS |
|
Image Super-Resolution (HP)
|
100% |
51374
1.90 KIPS |
|
Image Super-Resolution (Q)
|
97% |
123950
4.59 KIPS |
|
Text Classification (SP)
|
100% |
255
340.7 IPS |
|
Text Classification (HP)
|
100% |
3882
5.18 KIPS |
|
Text Classification (Q)
|
93% |
7873
10.6 KIPS |
|
Machine Translation (SP)
|
100% |
431
7.42 IPS |
|
Machine Translation (HP)
|
100% |
4036
69.5 IPS |
|
Machine Translation (Q)
|
56% |
2722
70.1 IPS |