Upload Date | April 25 2025 01:30 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-X926N |
Model ID | samsung SM-X926N |
Motherboard | gts10u |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3458 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 3 Cores @ 2.85 GHz |
Cluster 3 | 1 Core @ 3.40 GHz |
Memory Information | |
---|---|
Size | 10.96 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1693
314.9 IPS |
|
Image Classification (HP)
|
100% |
1817
337.8 IPS |
|
Image Classification (Q)
|
100% |
2646
492.0 IPS |
|
Image Segmentation (SP)
|
100% |
2111
34.2 IPS |
|
Image Segmentation (HP)
|
100% |
2105
34.1 IPS |
|
Image Segmentation (Q)
|
98% |
2803
45.6 IPS |
|
Pose Estimation (SP)
|
100% |
3300
3.85 IPS |
|
Pose Estimation (HP)
|
100% |
3122
3.64 IPS |
|
Pose Estimation (Q)
|
84% |
6530
7.74 IPS |
|
Object Detection (SP)
|
98% |
1377
109.6 IPS |
|
Object Detection (HP)
|
98% |
1347
107.2 IPS |
|
Object Detection (Q)
|
83% |
1933
156.1 IPS |
|
Face Detection (SP)
|
100% |
3010
35.8 IPS |
|
Face Detection (HP)
|
100% |
3028
36.0 IPS |
|
Face Detection (Q)
|
95% |
4671
55.8 IPS |
|
Depth Estimation (SP)
|
99% |
3903
30.2 IPS |
|
Depth Estimation (HP)
|
99% |
3854
29.8 IPS |
|
Depth Estimation (Q)
|
64% |
5757
52.7 IPS |
|
Style Transfer (SP)
|
89% |
7022
9.12 IPS |
|
Style Transfer (HP)
|
89% |
6958
9.03 IPS |
|
Style Transfer (Q)
|
98% |
12062
15.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
1613
59.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
1628
60.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
3289
121.9 IPS |
|
Text Classification (SP)
|
100% |
757
1.01 KIPS |
|
Text Classification (HP)
|
99% |
748
998.5 IPS |
|
Text Classification (Q)
|
88% |
1297
1.75 KIPS |
|
Machine Translation (SP)
|
100% |
1871
32.2 IPS |
|
Machine Translation (HP)
|
100% |
1746
30.1 IPS |
|
Machine Translation (Q)
|
50% |
828
29.4 IPS |