Upload Date | August 28 2025 06:00 AM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-X610 |
Model ID | samsung SM-X610 |
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 | 7.54 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
404
75.1 IPS |
|
Image Classification (HP)
|
100% |
397
73.9 IPS |
|
Image Classification (Q)
|
100% |
1064
197.9 IPS |
|
Image Segmentation (SP)
|
100% |
400
6.48 IPS |
|
Image Segmentation (HP)
|
100% |
413
6.69 IPS |
|
Image Segmentation (Q)
|
98% |
1276
20.8 IPS |
|
Pose Estimation (SP)
|
100% |
1872
2.18 IPS |
|
Pose Estimation (HP)
|
100% |
1797
2.10 IPS |
|
Pose Estimation (Q)
|
84% |
3211
3.81 IPS |
|
Object Detection (SP)
|
100% |
361
28.7 IPS |
|
Object Detection (HP)
|
100% |
350
27.7 IPS |
|
Object Detection (Q)
|
83% |
1001
80.8 IPS |
|
Face Detection (SP)
|
100% |
1032
12.3 IPS |
|
Face Detection (HP)
|
100% |
1031
12.3 IPS |
|
Face Detection (Q)
|
95% |
2442
29.2 IPS |
|
Depth Estimation (SP)
|
100% |
1348
10.4 IPS |
|
Depth Estimation (HP)
|
99% |
1369
10.5 IPS |
|
Depth Estimation (Q)
|
64% |
2472
22.6 IPS |
|
Style Transfer (SP)
|
89% |
2838
3.68 IPS |
|
Style Transfer (HP)
|
89% |
2734
3.55 IPS |
|
Style Transfer (Q)
|
98% |
6428
8.29 IPS |
|
Image Super-Resolution (SP)
|
100% |
772
28.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
773
28.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
1387
51.4 IPS |
|
Text Classification (SP)
|
100% |
338
451.4 IPS |
|
Text Classification (HP)
|
100% |
366
488.1 IPS |
|
Text Classification (Q)
|
88% |
653
880.9 IPS |
|
Machine Translation (SP)
|
100% |
564
9.72 IPS |
|
Machine Translation (HP)
|
100% |
463
7.97 IPS |
|
Machine Translation (Q)
|
50% |
305
10.8 IPS |