Upload Date | August 26 2025 09:04 AM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-M356B |
Model ID | samsung SM-M356B |
Motherboard | s5e8835 |
Governor | energy_aware |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 5.30 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
437
81.3 IPS |
|
Image Classification (HP)
|
100% |
409
76.1 IPS |
|
Image Classification (Q)
|
100% |
1001
186.1 IPS |
|
Image Segmentation (SP)
|
100% |
430
6.98 IPS |
|
Image Segmentation (HP)
|
100% |
389
6.31 IPS |
|
Image Segmentation (Q)
|
98% |
1193
19.4 IPS |
|
Pose Estimation (SP)
|
100% |
1512
1.76 IPS |
|
Pose Estimation (HP)
|
100% |
1508
1.76 IPS |
|
Pose Estimation (Q)
|
84% |
2627
3.12 IPS |
|
Object Detection (SP)
|
100% |
322
25.6 IPS |
|
Object Detection (HP)
|
100% |
314
24.9 IPS |
|
Object Detection (Q)
|
83% |
919
74.3 IPS |
|
Face Detection (SP)
|
100% |
1012
12.0 IPS |
|
Face Detection (HP)
|
100% |
877
10.4 IPS |
|
Face Detection (Q)
|
95% |
2285
27.3 IPS |
|
Depth Estimation (SP)
|
100% |
1121
8.64 IPS |
|
Depth Estimation (HP)
|
99% |
1248
9.62 IPS |
|
Depth Estimation (Q)
|
64% |
2261
20.7 IPS |
|
Style Transfer (SP)
|
89% |
2546
3.31 IPS |
|
Style Transfer (HP)
|
89% |
2563
3.33 IPS |
|
Style Transfer (Q)
|
98% |
5831
7.52 IPS |
|
Image Super-Resolution (SP)
|
100% |
641
23.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
748
27.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
1340
49.7 IPS |
|
Text Classification (SP)
|
100% |
336
448.9 IPS |
|
Text Classification (HP)
|
100% |
333
444.5 IPS |
|
Text Classification (Q)
|
88% |
609
821.0 IPS |
|
Machine Translation (SP)
|
100% |
507
8.73 IPS |
|
Machine Translation (HP)
|
100% |
495
8.53 IPS |
|
Machine Translation (Q)
|
50% |
317
11.3 IPS |