User | M91 |
Upload Date | August 19 2025 06:38 PM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-A366W |
Model ID | samsung SM-A366W |
Motherboard | parrot |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 2 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 5.16 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
401
74.6 IPS |
|
Image Classification (HP)
|
100% |
699
130.1 IPS |
|
Image Classification (Q)
|
100% |
648
120.5 IPS |
|
Image Segmentation (SP)
|
100% |
595
9.64 IPS |
|
Image Segmentation (HP)
|
100% |
1046
17.0 IPS |
|
Image Segmentation (Q)
|
98% |
971
15.8 IPS |
|
Pose Estimation (SP)
|
100% |
1979
2.31 IPS |
|
Pose Estimation (HP)
|
99% |
3783
4.43 IPS |
|
Pose Estimation (Q)
|
96% |
3764
4.41 IPS |
|
Object Detection (SP)
|
100% |
360
28.5 IPS |
|
Object Detection (HP)
|
99% |
599
47.6 IPS |
|
Object Detection (Q)
|
87% |
561
45.1 IPS |
|
Face Detection (SP)
|
100% |
1017
12.1 IPS |
|
Face Detection (HP)
|
100% |
2006
23.8 IPS |
|
Face Detection (Q)
|
97% |
1750
20.9 IPS |
|
Depth Estimation (SP)
|
100% |
1169
9.01 IPS |
|
Depth Estimation (HP)
|
98% |
2304
17.8 IPS |
|
Depth Estimation (Q)
|
61% |
1702
16.8 IPS |
|
Style Transfer (SP)
|
100% |
2158
2.77 IPS |
|
Style Transfer (HP)
|
100% |
4518
5.81 IPS |
|
Style Transfer (Q)
|
98% |
4477
5.77 IPS |
|
Image Super-Resolution (SP)
|
100% |
540
19.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
1018
37.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
979
36.3 IPS |
|
Text Classification (SP)
|
35% |
22
213.8 IPS |
|
Text Classification (HP)
|
35% |
35
313.9 IPS |
|
Text Classification (Q)
|
33% |
26
310.5 IPS |
|
Machine Translation (SP)
|
100% |
378
6.52 IPS |
|
Machine Translation (HP)
|
97% |
450
7.78 IPS |
|
Machine Translation (Q)
|
43% |
113
6.45 IPS |