User | M91 |
Upload Date | August 28 2025 02:19 AM |
Views | 5 |
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% |
400
74.3 IPS |
|
Image Classification (HP)
|
100% |
682
126.9 IPS |
|
Image Classification (Q)
|
100% |
641
119.3 IPS |
|
Image Segmentation (SP)
|
100% |
575
9.32 IPS |
|
Image Segmentation (HP)
|
100% |
1026
16.6 IPS |
|
Image Segmentation (Q)
|
98% |
960
15.6 IPS |
|
Pose Estimation (SP)
|
100% |
1968
2.30 IPS |
|
Pose Estimation (HP)
|
99% |
3807
4.46 IPS |
|
Pose Estimation (Q)
|
96% |
3751
4.40 IPS |
|
Object Detection (SP)
|
100% |
355
28.2 IPS |
|
Object Detection (HP)
|
99% |
595
47.2 IPS |
|
Object Detection (Q)
|
87% |
561
45.0 IPS |
|
Face Detection (SP)
|
100% |
1020
12.1 IPS |
|
Face Detection (HP)
|
100% |
1995
23.7 IPS |
|
Face Detection (Q)
|
97% |
1734
20.7 IPS |
|
Depth Estimation (SP)
|
100% |
1152
8.88 IPS |
|
Depth Estimation (HP)
|
98% |
2301
17.8 IPS |
|
Depth Estimation (Q)
|
61% |
1700
16.7 IPS |
|
Style Transfer (SP)
|
100% |
2157
2.77 IPS |
|
Style Transfer (HP)
|
100% |
4532
5.83 IPS |
|
Style Transfer (Q)
|
98% |
4519
5.83 IPS |
|
Image Super-Resolution (SP)
|
100% |
542
20.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
1023
37.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
996
36.9 IPS |
|
Text Classification (SP)
|
35% |
22
214.6 IPS |
|
Text Classification (HP)
|
35% |
34
311.4 IPS |
|
Text Classification (Q)
|
33% |
26
308.0 IPS |
|
Machine Translation (SP)
|
100% |
369
6.35 IPS |
|
Machine Translation (HP)
|
97% |
423
7.31 IPS |
|
Machine Translation (Q)
|
43% |
112
6.39 IPS |