Upload Date | January 02 2025 10:05 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
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% |
356
66.2 IPS |
|
Image Classification (HP)
|
100% |
357
66.4 IPS |
|
Image Classification (Q)
|
100% |
1041
193.5 IPS |
|
Image Segmentation (SP)
|
100% |
347
5.62 IPS |
|
Image Segmentation (HP)
|
100% |
393
6.38 IPS |
|
Image Segmentation (Q)
|
98% |
1158
18.8 IPS |
|
Pose Estimation (SP)
|
100% |
1597
1.86 IPS |
|
Pose Estimation (HP)
|
100% |
1493
1.74 IPS |
|
Pose Estimation (Q)
|
84% |
2837
3.36 IPS |
|
Object Detection (SP)
|
100% |
343
27.2 IPS |
|
Object Detection (HP)
|
100% |
342
27.1 IPS |
|
Object Detection (Q)
|
83% |
957
77.3 IPS |
|
Face Detection (SP)
|
100% |
866
10.3 IPS |
|
Face Detection (HP)
|
100% |
756
8.99 IPS |
|
Face Detection (Q)
|
95% |
2359
28.2 IPS |
|
Depth Estimation (SP)
|
100% |
1203
9.27 IPS |
|
Depth Estimation (HP)
|
99% |
1052
8.10 IPS |
|
Depth Estimation (Q)
|
64% |
2410
22.1 IPS |
|
Style Transfer (SP)
|
89% |
2930
3.80 IPS |
|
Style Transfer (HP)
|
89% |
2574
3.34 IPS |
|
Style Transfer (Q)
|
98% |
6186
7.98 IPS |
|
Image Super-Resolution (SP)
|
100% |
788
29.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
792
29.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
1460
54.1 IPS |
|
Text Classification (SP)
|
100% |
353
471.5 IPS |
|
Text Classification (HP)
|
100% |
351
467.9 IPS |
|
Text Classification (Q)
|
88% |
649
874.9 IPS |
|
Machine Translation (SP)
|
100% |
569
9.81 IPS |
|
Machine Translation (HP)
|
100% |
546
9.41 IPS |
|
Machine Translation (Q)
|
50% |
311
11.0 IPS |