Upload Date | September 21 2025 02:30 AM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 16 |
Model | samsung SM-F966W |
Model ID | samsung SM-F966W |
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% |
262
48.7 IPS |
|
Image Classification (HP)
|
100% |
265
49.3 IPS |
|
Image Classification (Q)
|
99% |
624
116.4 IPS |
|
Image Segmentation (SP)
|
100% |
349
5.65 IPS |
|
Image Segmentation (HP)
|
100% |
350
5.67 IPS |
|
Image Segmentation (Q)
|
98% |
664
10.8 IPS |
|
Pose Estimation (SP)
|
100% |
459
0.54 IPS |
|
Pose Estimation (HP)
|
100% |
443
0.52 IPS |
|
Pose Estimation (Q)
|
98% |
1827
2.14 IPS |
|
Object Detection (SP)
|
100% |
262
20.8 IPS |
|
Object Detection (HP)
|
100% |
263
20.9 IPS |
|
Object Detection (Q)
|
87% |
619
49.7 IPS |
|
Face Detection (SP)
|
100% |
704
8.36 IPS |
|
Face Detection (HP)
|
100% |
614
7.29 IPS |
|
Face Detection (Q)
|
97% |
1430
17.0 IPS |
|
Depth Estimation (SP)
|
100% |
588
4.53 IPS |
|
Depth Estimation (HP)
|
99% |
539
4.15 IPS |
|
Depth Estimation (Q)
|
64% |
1206
10.9 IPS |
|
Style Transfer (SP)
|
100% |
933
1.20 IPS |
|
Style Transfer (HP)
|
100% |
891
1.15 IPS |
|
Style Transfer (Q)
|
98% |
2645
3.41 IPS |
|
Image Super-Resolution (SP)
|
100% |
282
10.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
309
11.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
1088
40.3 IPS |
|
Text Classification (SP)
|
100% |
397
530.0 IPS |
|
Text Classification (HP)
|
100% |
397
530.1 IPS |
|
Text Classification (Q)
|
91% |
616
827.7 IPS |
|
Machine Translation (SP)
|
100% |
724
12.5 IPS |
|
Machine Translation (HP)
|
100% |
671
11.5 IPS |
|
Machine Translation (Q)
|
57% |
394
9.64 IPS |