User | Ncard00 |
Upload Date | March 28 2025 09:21 AM |
Views | 11 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S931B |
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% |
424
78.9 IPS |
|
Image Classification (HP)
|
100% |
422
78.5 IPS |
|
Image Classification (Q)
|
99% |
1053
196.4 IPS |
|
Image Segmentation (SP)
|
100% |
530
8.60 IPS |
|
Image Segmentation (HP)
|
100% |
500
8.11 IPS |
|
Image Segmentation (Q)
|
98% |
965
15.7 IPS |
|
Pose Estimation (SP)
|
100% |
584
0.68 IPS |
|
Pose Estimation (HP)
|
100% |
589
0.69 IPS |
|
Pose Estimation (Q)
|
98% |
2528
2.96 IPS |
|
Object Detection (SP)
|
100% |
353
28.0 IPS |
|
Object Detection (HP)
|
100% |
338
26.8 IPS |
|
Object Detection (Q)
|
87% |
754
60.4 IPS |
|
Face Detection (SP)
|
100% |
745
8.85 IPS |
|
Face Detection (HP)
|
100% |
854
10.2 IPS |
|
Face Detection (Q)
|
97% |
1966
23.4 IPS |
|
Depth Estimation (SP)
|
100% |
717
5.53 IPS |
|
Depth Estimation (HP)
|
99% |
706
5.44 IPS |
|
Depth Estimation (Q)
|
64% |
1589
14.4 IPS |
|
Style Transfer (SP)
|
100% |
1430
1.84 IPS |
|
Style Transfer (HP)
|
100% |
1359
1.75 IPS |
|
Style Transfer (Q)
|
98% |
3092
3.99 IPS |
|
Image Super-Resolution (SP)
|
100% |
340
12.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
430
15.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
1603
59.4 IPS |
|
Text Classification (SP)
|
100% |
579
772.2 IPS |
|
Text Classification (HP)
|
100% |
579
772.6 IPS |
|
Text Classification (Q)
|
91% |
890
1.20 KIPS |
|
Machine Translation (SP)
|
100% |
839
14.4 IPS |
|
Machine Translation (HP)
|
100% |
947
16.3 IPS |
|
Machine Translation (Q)
|
57% |
617
15.1 IPS |