Upload Date | April 13 2025 01:10 PM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Samsung Exynos 1380 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy A54 |
Model ID | samsung SM-A5460 |
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% |
400
74.4 IPS |
|
Image Classification (HP)
|
100% |
393
73.1 IPS |
|
Image Classification (Q)
|
100% |
1273
236.7 IPS |
|
Image Segmentation (SP)
|
100% |
454
7.36 IPS |
|
Image Segmentation (HP)
|
100% |
444
7.20 IPS |
|
Image Segmentation (Q)
|
98% |
1434
23.3 IPS |
|
Pose Estimation (SP)
|
100% |
1570
1.83 IPS |
|
Pose Estimation (HP)
|
100% |
1642
1.92 IPS |
|
Pose Estimation (Q)
|
84% |
2666
3.16 IPS |
|
Object Detection (SP)
|
100% |
348
27.6 IPS |
|
Object Detection (HP)
|
100% |
360
28.6 IPS |
|
Object Detection (Q)
|
83% |
1074
86.8 IPS |
|
Face Detection (SP)
|
100% |
910
10.8 IPS |
|
Face Detection (HP)
|
100% |
919
10.9 IPS |
|
Face Detection (Q)
|
95% |
2614
31.2 IPS |
|
Depth Estimation (SP)
|
100% |
1238
9.54 IPS |
|
Depth Estimation (HP)
|
99% |
1243
9.58 IPS |
|
Depth Estimation (Q)
|
64% |
2386
21.8 IPS |
|
Style Transfer (SP)
|
89% |
2707
3.51 IPS |
|
Style Transfer (HP)
|
89% |
2824
3.67 IPS |
|
Style Transfer (Q)
|
98% |
6486
8.36 IPS |
|
Image Super-Resolution (SP)
|
100% |
695
25.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
766
28.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
1470
54.5 IPS |
|
Text Classification (SP)
|
100% |
350
467.5 IPS |
|
Text Classification (HP)
|
100% |
355
474.0 IPS |
|
Text Classification (Q)
|
88% |
657
885.7 IPS |
|
Machine Translation (SP)
|
100% |
584
10.1 IPS |
|
Machine Translation (HP)
|
100% |
522
9.00 IPS |
|
Machine Translation (Q)
|
50% |
321
11.4 IPS |