| Upload Date | November 22 2026 02:41 AM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | ARM ARMv8 |
| System Information | |
|---|---|
| Operating System | Android 17 |
| Model | samsung SM-X940 |
| Model ID | samsung SM-X940 |
| Motherboard | gts12uwifi |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3468 revision 0 |
| Base Frequency | 2.70 GHz |
| Cluster 1 | 4 Cores @ 2.70 GHz |
| Cluster 2 | 3 Cores @ 3.50 GHz |
| Cluster 3 | 1 Core @ 4.21 GHz |
| Memory Information | |
|---|---|
| Size | 15.10 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
602
111.9 IPS |
|
|
Image Classification (HP)
|
100% |
836
155.6 IPS |
|
|
Image Classification (Q)
|
97% |
764
142.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
2461
39.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
3496
56.7 IPS |
|
|
Image Segmentation (Q)
|
98% |
3262
53.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
12926
15.1 IPS |
|
|
Pose Estimation (HP)
|
100% |
21556
25.2 IPS |
|
|
Pose Estimation (Q)
|
95% |
21826
25.6 IPS |
|
|
Object Detection (SP)
|
100% |
634
50.3 IPS |
|
|
Object Detection (HP)
|
99% |
913
72.4 IPS |
|
|
Object Detection (Q)
|
83% |
819
66.1 IPS |
|
|
Face Detection (SP)
|
100% |
3945
46.9 IPS |
|
|
Face Detection (HP)
|
100% |
5182
61.6 IPS |
|
|
Face Detection (Q)
|
96% |
4957
59.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
4314
33.2 IPS |
|
|
Depth Estimation (HP)
|
98% |
5546
42.9 IPS |
|
|
Depth Estimation (Q)
|
62% |
4449
42.3 IPS |
|
|
Style Transfer (SP)
|
100% |
17653
22.7 IPS |
|
|
Style Transfer (HP)
|
100% |
30962
39.8 IPS |
|
|
Style Transfer (Q)
|
98% |
31570
40.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1832
67.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3140
115.9 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
2396
88.8 IPS |
|
|
Text Classification (SP)
|
35% |
28
252.8 IPS |
|
|
Text Classification (HP)
|
29% |
23
403.4 IPS |
|
|
Text Classification (Q)
|
32% |
25
320.1 IPS |
|
|
Machine Translation (SP)
|
100% |
425
7.32 IPS |
|
|
Machine Translation (HP)
|
100% |
506
8.71 IPS |
|
|
Machine Translation (Q)
|
43% |
119
6.90 IPS |