User | M91 |
Upload Date | August 19 2025 02:47 AM |
Views | 6 |
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% |
406
75.6 IPS |
|
Image Classification (HP)
|
100% |
692
128.8 IPS |
|
Image Classification (Q)
|
100% |
644
119.8 IPS |
|
Image Segmentation (SP)
|
100% |
573
9.28 IPS |
|
Image Segmentation (HP)
|
100% |
1054
17.1 IPS |
|
Image Segmentation (Q)
|
98% |
988
16.1 IPS |
|
Pose Estimation (SP)
|
100% |
1983
2.31 IPS |
|
Pose Estimation (HP)
|
99% |
3802
4.45 IPS |
|
Pose Estimation (Q)
|
96% |
3756
4.40 IPS |
|
Object Detection (SP)
|
100% |
359
28.5 IPS |
|
Object Detection (HP)
|
99% |
598
47.4 IPS |
|
Object Detection (Q)
|
87% |
565
45.4 IPS |
|
Face Detection (SP)
|
100% |
1018
12.1 IPS |
|
Face Detection (HP)
|
100% |
2023
24.0 IPS |
|
Face Detection (Q)
|
97% |
1742
20.8 IPS |
|
Depth Estimation (SP)
|
100% |
1173
9.04 IPS |
|
Depth Estimation (HP)
|
98% |
2301
17.8 IPS |
|
Depth Estimation (Q)
|
61% |
1715
16.9 IPS |
|
Style Transfer (SP)
|
100% |
2104
2.71 IPS |
|
Style Transfer (HP)
|
100% |
4517
5.81 IPS |
|
Style Transfer (Q)
|
98% |
4505
5.81 IPS |
|
Image Super-Resolution (SP)
|
100% |
538
19.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
1014
37.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
986
36.5 IPS |
|
Text Classification (SP)
|
35% |
22
214.7 IPS |
|
Text Classification (HP)
|
35% |
34
312.4 IPS |
|
Text Classification (Q)
|
33% |
26
309.4 IPS |
|
Machine Translation (SP)
|
100% |
385
6.63 IPS |
|
Machine Translation (HP)
|
97% |
431
7.46 IPS |
|
Machine Translation (Q)
|
43% |
117
6.66 IPS |