Upload Date | January 03 2025 09:18 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A356E |
Model ID | samsung SM-A356E |
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% |
439
81.6 IPS |
|
Image Classification (HP)
|
100% |
422
78.4 IPS |
|
Image Classification (Q)
|
100% |
1188
220.9 IPS |
|
Image Segmentation (SP)
|
100% |
457
7.42 IPS |
|
Image Segmentation (HP)
|
100% |
449
7.27 IPS |
|
Image Segmentation (Q)
|
98% |
1193
19.4 IPS |
|
Pose Estimation (SP)
|
100% |
1542
1.80 IPS |
|
Pose Estimation (HP)
|
100% |
1549
1.81 IPS |
|
Pose Estimation (Q)
|
84% |
2702
3.20 IPS |
|
Object Detection (SP)
|
100% |
322
25.5 IPS |
|
Object Detection (HP)
|
100% |
326
25.9 IPS |
|
Object Detection (Q)
|
83% |
975
78.7 IPS |
|
Face Detection (SP)
|
100% |
1024
12.2 IPS |
|
Face Detection (HP)
|
100% |
910
10.8 IPS |
|
Face Detection (Q)
|
95% |
2412
28.8 IPS |
|
Depth Estimation (SP)
|
100% |
1158
8.92 IPS |
|
Depth Estimation (HP)
|
99% |
1257
9.68 IPS |
|
Depth Estimation (Q)
|
64% |
2297
21.0 IPS |
|
Style Transfer (SP)
|
89% |
2622
3.40 IPS |
|
Style Transfer (HP)
|
89% |
2633
3.42 IPS |
|
Style Transfer (Q)
|
98% |
5973
7.70 IPS |
|
Image Super-Resolution (SP)
|
100% |
688
25.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
660
24.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
1382
51.2 IPS |
|
Text Classification (SP)
|
100% |
336
448.4 IPS |
|
Text Classification (HP)
|
100% |
329
439.1 IPS |
|
Text Classification (Q)
|
88% |
617
831.5 IPS |
|
Machine Translation (SP)
|
100% |
514
8.85 IPS |
|
Machine Translation (HP)
|
100% |
506
8.72 IPS |
|
Machine Translation (Q)
|
50% |
320
11.4 IPS |