Upload Date | August 04 2025 03:10 PM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 16 |
Model | samsung SM-F966U1 |
Model ID | samsung SM-F966U1 |
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% |
2102
390.9 IPS |
|
Image Classification (HP)
|
100% |
2138
397.6 IPS |
|
Image Classification (Q)
|
100% |
4556
847.4 IPS |
|
Image Segmentation (SP)
|
100% |
2367
38.4 IPS |
|
Image Segmentation (HP)
|
100% |
2306
37.4 IPS |
|
Image Segmentation (Q)
|
98% |
5148
83.7 IPS |
|
Pose Estimation (SP)
|
100% |
5143
6.00 IPS |
|
Pose Estimation (HP)
|
100% |
3506
4.09 IPS |
|
Pose Estimation (Q)
|
84% |
8239
9.77 IPS |
|
Object Detection (SP)
|
98% |
1085
86.4 IPS |
|
Object Detection (HP)
|
98% |
1077
85.7 IPS |
|
Object Detection (Q)
|
83% |
2758
222.8 IPS |
|
Face Detection (SP)
|
100% |
3321
39.5 IPS |
|
Face Detection (HP)
|
100% |
3386
40.2 IPS |
|
Face Detection (Q)
|
95% |
7081
84.5 IPS |
|
Depth Estimation (SP)
|
99% |
3739
28.9 IPS |
|
Depth Estimation (HP)
|
99% |
3436
26.5 IPS |
|
Depth Estimation (Q)
|
64% |
5918
54.2 IPS |
|
Style Transfer (SP)
|
89% |
7904
10.3 IPS |
|
Style Transfer (HP)
|
89% |
7531
9.78 IPS |
|
Style Transfer (Q)
|
98% |
13282
17.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
1439
53.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
1612
59.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
4254
157.6 IPS |
|
Text Classification (SP)
|
100% |
738
985.4 IPS |
|
Text Classification (HP)
|
99% |
813
1.08 KIPS |
|
Text Classification (Q)
|
88% |
580
782.5 IPS |
|
Machine Translation (SP)
|
100% |
1252
21.6 IPS |
|
Machine Translation (HP)
|
100% |
954
16.4 IPS |
|
Machine Translation (Q)
|
50% |
387
13.7 IPS |