Upload Date | June 20 2025 10:00 AM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-M366B |
Model ID | samsung SM-M366B |
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 | 7.26 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
420
78.2 IPS |
|
Image Classification (HP)
|
100% |
427
79.4 IPS |
|
Image Classification (Q)
|
100% |
1373
255.4 IPS |
|
Image Segmentation (SP)
|
100% |
520
8.42 IPS |
|
Image Segmentation (HP)
|
100% |
403
6.53 IPS |
|
Image Segmentation (Q)
|
98% |
1164
18.9 IPS |
|
Pose Estimation (SP)
|
100% |
1725
2.01 IPS |
|
Pose Estimation (HP)
|
100% |
1663
1.94 IPS |
|
Pose Estimation (Q)
|
84% |
2830
3.36 IPS |
|
Object Detection (SP)
|
100% |
346
27.5 IPS |
|
Object Detection (HP)
|
100% |
345
27.4 IPS |
|
Object Detection (Q)
|
83% |
1021
82.5 IPS |
|
Face Detection (SP)
|
100% |
894
10.6 IPS |
|
Face Detection (HP)
|
100% |
894
10.6 IPS |
|
Face Detection (Q)
|
95% |
2546
30.4 IPS |
|
Depth Estimation (SP)
|
100% |
1220
9.40 IPS |
|
Depth Estimation (HP)
|
99% |
1121
8.63 IPS |
|
Depth Estimation (Q)
|
64% |
2581
23.6 IPS |
|
Style Transfer (SP)
|
89% |
2865
3.72 IPS |
|
Style Transfer (HP)
|
89% |
2641
3.43 IPS |
|
Style Transfer (Q)
|
98% |
6209
8.01 IPS |
|
Image Super-Resolution (SP)
|
100% |
695
25.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
780
28.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
1479
54.8 IPS |
|
Text Classification (SP)
|
100% |
343
458.4 IPS |
|
Text Classification (HP)
|
100% |
336
449.0 IPS |
|
Text Classification (Q)
|
88% |
652
879.9 IPS |
|
Machine Translation (SP)
|
100% |
561
9.66 IPS |
|
Machine Translation (HP)
|
100% |
520
8.95 IPS |
|
Machine Translation (Q)
|
50% |
322
11.4 IPS |