Upload Date | July 15 2025 12:21 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
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% |
2187
406.8 IPS |
|
Image Classification (HP)
|
100% |
2170
403.5 IPS |
|
Image Classification (Q)
|
100% |
4650
864.8 IPS |
|
Image Segmentation (SP)
|
100% |
2469
40.0 IPS |
|
Image Segmentation (HP)
|
100% |
2397
38.9 IPS |
|
Image Segmentation (Q)
|
98% |
5452
88.6 IPS |
|
Pose Estimation (SP)
|
100% |
5287
6.17 IPS |
|
Pose Estimation (HP)
|
100% |
3916
4.57 IPS |
|
Pose Estimation (Q)
|
84% |
10223
12.1 IPS |
|
Object Detection (SP)
|
98% |
1360
108.2 IPS |
|
Object Detection (HP)
|
98% |
1323
105.3 IPS |
|
Object Detection (Q)
|
83% |
3298
266.4 IPS |
|
Face Detection (SP)
|
100% |
4304
51.1 IPS |
|
Face Detection (HP)
|
100% |
3997
47.5 IPS |
|
Face Detection (Q)
|
95% |
8825
105.4 IPS |
|
Depth Estimation (SP)
|
99% |
4422
34.2 IPS |
|
Depth Estimation (HP)
|
99% |
3998
30.9 IPS |
|
Depth Estimation (Q)
|
64% |
7734
70.8 IPS |
|
Style Transfer (SP)
|
89% |
9567
12.4 IPS |
|
Style Transfer (HP)
|
89% |
9474
12.3 IPS |
|
Style Transfer (Q)
|
98% |
19573
25.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
2059
76.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
2020
74.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
4773
176.9 IPS |
|
Text Classification (SP)
|
100% |
727
970.1 IPS |
|
Text Classification (HP)
|
99% |
740
987.2 IPS |
|
Text Classification (Q)
|
88% |
597
805.4 IPS |
|
Machine Translation (SP)
|
100% |
1404
24.2 IPS |
|
Machine Translation (HP)
|
100% |
1109
19.1 IPS |
|
Machine Translation (Q)
|
50% |
455
16.1 IPS |