| Upload Date | November 15 2025 03:49 AM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | ARM ARMv8 |
| System Information | |
|---|---|
| Operating System | Android 16 |
| Model | samsung SM-F766N |
| Model ID | samsung SM-F766N |
| Motherboard | s5e9955 |
| Governor | energy_aware |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 10 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3461 revision 1 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 2 Cores @ 1.80 GHz |
| Cluster 2 | 5 Cores @ 2.36 GHz |
| Cluster 3 | 2 Cores @ 2.75 GHz |
| Cluster 4 | 1 Core @ 3.30 GHz |
| Memory Information | |
|---|---|
| Size | 10.95 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1058
196.8 IPS |
|
|
Image Classification (HP)
|
100% |
1658
308.3 IPS |
|
|
Image Classification (Q)
|
100% |
1418
263.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
2205
35.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
3547
57.5 IPS |
|
|
Image Segmentation (Q)
|
98% |
2934
47.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
9521
11.1 IPS |
|
|
Pose Estimation (HP)
|
99% |
15907
18.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
17674
20.7 IPS |
|
|
Object Detection (SP)
|
100% |
857
68.0 IPS |
|
|
Object Detection (HP)
|
99% |
1271
100.8 IPS |
|
|
Object Detection (Q)
|
84% |
1090
87.9 IPS |
|
|
Face Detection (SP)
|
100% |
3674
43.7 IPS |
|
|
Face Detection (HP)
|
100% |
5405
64.2 IPS |
|
|
Face Detection (Q)
|
97% |
4882
58.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
4973
38.3 IPS |
|
|
Depth Estimation (HP)
|
98% |
7707
59.6 IPS |
|
|
Depth Estimation (Q)
|
62% |
5894
56.8 IPS |
|
|
Style Transfer (SP)
|
100% |
18362
23.6 IPS |
|
|
Style Transfer (HP)
|
100% |
25982
33.4 IPS |
|
|
Style Transfer (Q)
|
98% |
25791
33.3 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2799
103.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4225
156.0 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
4250
157.5 IPS |
|
|
Text Classification (SP)
|
29% |
29
508.4 IPS |
|
|
Text Classification (HP)
|
35% |
54
495.5 IPS |
|
|
Text Classification (Q)
|
29% |
24
417.2 IPS |
|
|
Machine Translation (SP)
|
100% |
850
14.6 IPS |
|
|
Machine Translation (HP)
|
100% |
1123
19.3 IPS |
|
|
Machine Translation (Q)
|
42% |
224
14.5 IPS |