Upload Date | March 28 2025 01:56 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-A266B |
Model ID | samsung SM-A266B |
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% |
414
77.0 IPS |
|
Image Classification (HP)
|
100% |
400
74.4 IPS |
|
Image Classification (Q)
|
100% |
1069
198.9 IPS |
|
Image Segmentation (SP)
|
100% |
433
7.02 IPS |
|
Image Segmentation (HP)
|
100% |
428
6.94 IPS |
|
Image Segmentation (Q)
|
98% |
1271
20.7 IPS |
|
Pose Estimation (SP)
|
100% |
1757
2.05 IPS |
|
Pose Estimation (HP)
|
100% |
1530
1.79 IPS |
|
Pose Estimation (Q)
|
84% |
2563
3.04 IPS |
|
Object Detection (SP)
|
100% |
323
25.6 IPS |
|
Object Detection (HP)
|
100% |
324
25.7 IPS |
|
Object Detection (Q)
|
83% |
921
74.4 IPS |
|
Face Detection (SP)
|
100% |
881
10.5 IPS |
|
Face Detection (HP)
|
100% |
884
10.5 IPS |
|
Face Detection (Q)
|
95% |
2288
27.3 IPS |
|
Depth Estimation (SP)
|
100% |
1141
8.79 IPS |
|
Depth Estimation (HP)
|
99% |
1150
8.86 IPS |
|
Depth Estimation (Q)
|
64% |
2298
21.0 IPS |
|
Style Transfer (SP)
|
89% |
2629
3.41 IPS |
|
Style Transfer (HP)
|
89% |
2582
3.35 IPS |
|
Style Transfer (Q)
|
98% |
5966
7.69 IPS |
|
Image Super-Resolution (SP)
|
100% |
696
25.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
677
25.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
1378
51.1 IPS |
|
Text Classification (SP)
|
100% |
333
444.0 IPS |
|
Text Classification (HP)
|
100% |
332
443.1 IPS |
|
Text Classification (Q)
|
88% |
618
833.3 IPS |
|
Machine Translation (SP)
|
100% |
526
9.05 IPS |
|
Machine Translation (HP)
|
100% |
501
8.62 IPS |
|
Machine Translation (Q)
|
50% |
315
11.2 IPS |