Upload Date | December 25 2024 07:34 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
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% |
449
83.5 IPS |
|
Image Classification (HP)
|
100% |
433
80.6 IPS |
|
Image Classification (Q)
|
100% |
1376
256.0 IPS |
|
Image Segmentation (SP)
|
100% |
515
8.35 IPS |
|
Image Segmentation (HP)
|
100% |
516
8.37 IPS |
|
Image Segmentation (Q)
|
98% |
1605
26.1 IPS |
|
Pose Estimation (SP)
|
100% |
1896
2.21 IPS |
|
Pose Estimation (HP)
|
100% |
1837
2.14 IPS |
|
Pose Estimation (Q)
|
84% |
3372
4.00 IPS |
|
Object Detection (SP)
|
100% |
402
31.9 IPS |
|
Object Detection (HP)
|
100% |
395
31.3 IPS |
|
Object Detection (Q)
|
83% |
1045
84.4 IPS |
|
Face Detection (SP)
|
100% |
961
11.4 IPS |
|
Face Detection (HP)
|
100% |
958
11.4 IPS |
|
Face Detection (Q)
|
95% |
3259
38.9 IPS |
|
Depth Estimation (SP)
|
100% |
1497
11.5 IPS |
|
Depth Estimation (HP)
|
99% |
1463
11.3 IPS |
|
Depth Estimation (Q)
|
64% |
3063
28.1 IPS |
|
Style Transfer (SP)
|
89% |
3265
4.24 IPS |
|
Style Transfer (HP)
|
89% |
3204
4.16 IPS |
|
Style Transfer (Q)
|
98% |
7592
9.79 IPS |
|
Image Super-Resolution (SP)
|
100% |
828
30.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
744
27.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
1616
59.9 IPS |
|
Text Classification (SP)
|
100% |
408
544.1 IPS |
|
Text Classification (HP)
|
100% |
420
561.1 IPS |
|
Text Classification (Q)
|
88% |
804
1.08 KIPS |
|
Machine Translation (SP)
|
100% |
635
10.9 IPS |
|
Machine Translation (HP)
|
100% |
622
10.7 IPS |
|
Machine Translation (Q)
|
50% |
368
13.1 IPS |