Upload Date | September 26 2025 02:35 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 16 |
Model | samsung SM-X936N |
Model ID | samsung SM-X936N |
Motherboard | gts11u |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3461 revision 1 |
Base Frequency | 2.40 GHz |
Cluster 1 | 4 Cores @ 2.40 GHz |
Cluster 2 | 3 Cores @ 3.30 GHz |
Cluster 3 | 1 Core @ 3.73 GHz |
Memory Information | |
---|---|
Size | 10.99 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
548
101.9 IPS |
|
Image Classification (HP)
|
100% |
776
144.3 IPS |
|
Image Classification (Q)
|
97% |
1044
194.9 IPS |
|
Image Segmentation (SP)
|
100% |
2071
33.6 IPS |
|
Image Segmentation (HP)
|
100% |
2882
46.7 IPS |
|
Image Segmentation (Q)
|
98% |
3038
49.4 IPS |
|
Pose Estimation (SP)
|
100% |
9268
10.8 IPS |
|
Pose Estimation (HP)
|
100% |
15995
18.7 IPS |
|
Pose Estimation (Q)
|
95% |
15730
18.4 IPS |
|
Object Detection (SP)
|
100% |
536
42.5 IPS |
|
Object Detection (HP)
|
99% |
802
63.6 IPS |
|
Object Detection (Q)
|
83% |
866
69.9 IPS |
|
Face Detection (SP)
|
100% |
3056
36.3 IPS |
|
Face Detection (HP)
|
100% |
4430
52.6 IPS |
|
Face Detection (Q)
|
96% |
3754
44.8 IPS |
|
Depth Estimation (SP)
|
100% |
3674
28.3 IPS |
|
Depth Estimation (HP)
|
98% |
5712
44.1 IPS |
|
Depth Estimation (Q)
|
62% |
4629
44.0 IPS |
|
Style Transfer (SP)
|
100% |
13691
17.6 IPS |
|
Style Transfer (HP)
|
100% |
25803
33.2 IPS |
|
Style Transfer (Q)
|
98% |
25791
33.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
1975
72.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
2566
94.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
2374
88.0 IPS |
|
Text Classification (SP)
|
35% |
23
213.1 IPS |
|
Text Classification (HP)
|
29% |
16
275.3 IPS |
|
Text Classification (Q)
|
32% |
19
248.3 IPS |
|
Machine Translation (SP)
|
100% |
466
8.02 IPS |
|
Machine Translation (HP)
|
100% |
552
9.50 IPS |
|
Machine Translation (Q)
|
43% |
135
7.86 IPS |