Upload Date | September 19 2024 03:31 AM |
Views | 1 |
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% |
439
81.6 IPS |
|
Image Classification (HP)
|
100% |
422
78.4 IPS |
|
Image Classification (Q)
|
100% |
1362
253.3 IPS |
|
Image Segmentation (SP)
|
100% |
503
8.15 IPS |
|
Image Segmentation (HP)
|
100% |
488
7.91 IPS |
|
Image Segmentation (Q)
|
98% |
1559
25.4 IPS |
|
Pose Estimation (SP)
|
100% |
1798
2.10 IPS |
|
Pose Estimation (HP)
|
100% |
1762
2.06 IPS |
|
Pose Estimation (Q)
|
84% |
3285
3.90 IPS |
|
Object Detection (SP)
|
100% |
378
30.0 IPS |
|
Object Detection (HP)
|
100% |
375
29.8 IPS |
|
Object Detection (Q)
|
83% |
1132
91.4 IPS |
|
Face Detection (SP)
|
100% |
1084
12.9 IPS |
|
Face Detection (HP)
|
100% |
890
10.6 IPS |
|
Face Detection (Q)
|
95% |
2737
32.7 IPS |
|
Depth Estimation (SP)
|
100% |
1275
9.82 IPS |
|
Depth Estimation (HP)
|
99% |
1275
9.82 IPS |
|
Depth Estimation (Q)
|
64% |
2838
26.0 IPS |
|
Style Transfer (SP)
|
89% |
2923
3.79 IPS |
|
Style Transfer (HP)
|
89% |
2904
3.77 IPS |
|
Style Transfer (Q)
|
98% |
6627
8.55 IPS |
|
Image Super-Resolution (SP)
|
100% |
683
25.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
825
30.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
1626
60.3 IPS |
|
Text Classification (SP)
|
100% |
385
514.3 IPS |
|
Text Classification (HP)
|
100% |
391
521.2 IPS |
|
Text Classification (Q)
|
88% |
735
991.3 IPS |
|
Machine Translation (SP)
|
100% |
591
10.2 IPS |
|
Machine Translation (HP)
|
100% |
582
10.0 IPS |
|
Machine Translation (Q)
|
50% |
313
11.1 IPS |