Upload Date | August 20 2025 11:19 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 16 |
Model | samsung SM-F966B |
Model ID | samsung SM-F966B |
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 | 10.85 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
423
78.7 IPS |
|
Image Classification (HP)
|
100% |
377
70.1 IPS |
|
Image Classification (Q)
|
99% |
684
127.6 IPS |
|
Image Segmentation (SP)
|
100% |
400
6.49 IPS |
|
Image Segmentation (HP)
|
100% |
372
6.04 IPS |
|
Image Segmentation (Q)
|
98% |
701
11.4 IPS |
|
Pose Estimation (SP)
|
100% |
466
0.54 IPS |
|
Pose Estimation (HP)
|
100% |
420
0.49 IPS |
|
Pose Estimation (Q)
|
98% |
1757
2.06 IPS |
|
Object Detection (SP)
|
100% |
262
20.8 IPS |
|
Object Detection (HP)
|
100% |
264
21.0 IPS |
|
Object Detection (Q)
|
87% |
692
55.5 IPS |
|
Face Detection (SP)
|
100% |
695
8.26 IPS |
|
Face Detection (HP)
|
100% |
640
7.61 IPS |
|
Face Detection (Q)
|
97% |
1249
14.9 IPS |
|
Depth Estimation (SP)
|
100% |
563
4.34 IPS |
|
Depth Estimation (HP)
|
99% |
564
4.34 IPS |
|
Depth Estimation (Q)
|
64% |
1221
11.1 IPS |
|
Style Transfer (SP)
|
100% |
980
1.26 IPS |
|
Style Transfer (HP)
|
100% |
905
1.16 IPS |
|
Style Transfer (Q)
|
98% |
2683
3.46 IPS |
|
Image Super-Resolution (SP)
|
100% |
289
10.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
308
11.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
1104
40.9 IPS |
|
Text Classification (SP)
|
100% |
398
531.6 IPS |
|
Text Classification (HP)
|
100% |
432
577.0 IPS |
|
Text Classification (Q)
|
91% |
668
898.4 IPS |
|
Machine Translation (SP)
|
100% |
752
13.0 IPS |
|
Machine Translation (HP)
|
100% |
682
11.7 IPS |
|
Machine Translation (Q)
|
57% |
435
10.6 IPS |