User | harsidh |
Upload Date | July 06 2025 08:54 AM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
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% |
252
46.9 IPS |
|
Image Classification (HP)
|
100% |
200
37.2 IPS |
|
Image Classification (Q)
|
97% |
165
30.8 IPS |
|
Image Segmentation (SP)
|
100% |
589
9.55 IPS |
|
Image Segmentation (HP)
|
100% |
1176
19.1 IPS |
|
Image Segmentation (Q)
|
98% |
1169
19.0 IPS |
|
Pose Estimation (SP)
|
100% |
2487
2.90 IPS |
|
Pose Estimation (HP)
|
100% |
4883
5.70 IPS |
|
Pose Estimation (Q)
|
95% |
4788
5.61 IPS |
|
Object Detection (SP)
|
100% |
369
29.3 IPS |
|
Object Detection (HP)
|
99% |
478
37.9 IPS |
|
Object Detection (Q)
|
83% |
441
35.6 IPS |
|
Face Detection (SP)
|
100% |
1235
14.7 IPS |
|
Face Detection (HP)
|
100% |
1890
22.5 IPS |
|
Face Detection (Q)
|
96% |
1896
22.6 IPS |
|
Depth Estimation (SP)
|
100% |
1641
12.6 IPS |
|
Depth Estimation (HP)
|
98% |
2890
22.3 IPS |
|
Depth Estimation (Q)
|
62% |
2259
21.5 IPS |
|
Style Transfer (SP)
|
100% |
3968
5.10 IPS |
|
Style Transfer (HP)
|
100% |
8958
11.5 IPS |
|
Style Transfer (Q)
|
98% |
8682
11.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
875
32.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
1296
47.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
1266
46.9 IPS |
|
Text Classification (SP)
|
35% |
6
58.2 IPS |
|
Text Classification (HP)
|
35% |
9
86.3 IPS |
|
Text Classification (Q)
|
32% |
7
87.6 IPS |
|
Machine Translation (SP)
|
100% |
215
3.70 IPS |
|
Machine Translation (HP)
|
100% |
162
2.80 IPS |
|
Machine Translation (Q)
|
43% |
43
2.52 IPS |