User | M91 |
Upload Date | August 27 2025 06:48 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% |
405
75.3 IPS |
|
Image Classification (HP)
|
100% |
683
127.1 IPS |
|
Image Classification (Q)
|
100% |
640
119.0 IPS |
|
Image Segmentation (SP)
|
100% |
585
9.48 IPS |
|
Image Segmentation (HP)
|
100% |
1047
17.0 IPS |
|
Image Segmentation (Q)
|
98% |
976
15.9 IPS |
|
Pose Estimation (SP)
|
100% |
1972
2.30 IPS |
|
Pose Estimation (HP)
|
99% |
3806
4.45 IPS |
|
Pose Estimation (Q)
|
96% |
3752
4.40 IPS |
|
Object Detection (SP)
|
100% |
358
28.4 IPS |
|
Object Detection (HP)
|
99% |
602
47.7 IPS |
|
Object Detection (Q)
|
87% |
565
45.4 IPS |
|
Face Detection (SP)
|
100% |
1024
12.2 IPS |
|
Face Detection (HP)
|
100% |
2023
24.0 IPS |
|
Face Detection (Q)
|
97% |
1739
20.7 IPS |
|
Depth Estimation (SP)
|
100% |
1174
9.04 IPS |
|
Depth Estimation (HP)
|
98% |
2311
17.9 IPS |
|
Depth Estimation (Q)
|
61% |
1717
16.9 IPS |
|
Style Transfer (SP)
|
100% |
2165
2.78 IPS |
|
Style Transfer (HP)
|
100% |
4533
5.83 IPS |
|
Style Transfer (Q)
|
98% |
4515
5.82 IPS |
|
Image Super-Resolution (SP)
|
100% |
515
19.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
1023
37.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
991
36.7 IPS |
|
Text Classification (SP)
|
35% |
22
211.6 IPS |
|
Text Classification (HP)
|
35% |
34
311.2 IPS |
|
Text Classification (Q)
|
33% |
26
308.8 IPS |
|
Machine Translation (SP)
|
100% |
373
6.43 IPS |
|
Machine Translation (HP)
|
97% |
425
7.36 IPS |
|
Machine Translation (Q)
|
43% |
111
6.29 IPS |