Upload Date | July 14 2025 04:16 PM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-X216B |
Model ID | samsung SM-X216B |
Motherboard | holi |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.21 GHz |
Memory Information | |
---|---|
Size | 7.21 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
240
44.6 IPS |
|
Image Classification (HP)
|
100% |
235
43.7 IPS |
|
Image Classification (Q)
|
100% |
728
135.3 IPS |
|
Image Segmentation (SP)
|
100% |
304
4.93 IPS |
|
Image Segmentation (HP)
|
100% |
311
5.03 IPS |
|
Image Segmentation (Q)
|
98% |
830
13.5 IPS |
|
Pose Estimation (SP)
|
100% |
1079
1.26 IPS |
|
Pose Estimation (HP)
|
100% |
1022
1.19 IPS |
|
Pose Estimation (Q)
|
84% |
1564
1.86 IPS |
|
Object Detection (SP)
|
100% |
212
16.8 IPS |
|
Object Detection (HP)
|
100% |
214
17.0 IPS |
|
Object Detection (Q)
|
83% |
720
58.2 IPS |
|
Face Detection (SP)
|
100% |
718
8.53 IPS |
|
Face Detection (HP)
|
100% |
730
8.67 IPS |
|
Face Detection (Q)
|
95% |
1609
19.2 IPS |
|
Depth Estimation (SP)
|
100% |
931
7.17 IPS |
|
Depth Estimation (HP)
|
99% |
910
7.01 IPS |
|
Depth Estimation (Q)
|
64% |
1482
13.6 IPS |
|
Style Transfer (SP)
|
89% |
1799
2.33 IPS |
|
Style Transfer (HP)
|
89% |
1806
2.34 IPS |
|
Style Transfer (Q)
|
98% |
3617
4.66 IPS |
|
Image Super-Resolution (SP)
|
100% |
508
18.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
506
18.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
990
36.7 IPS |
|
Text Classification (SP)
|
100% |
276
368.1 IPS |
|
Text Classification (HP)
|
100% |
271
361.5 IPS |
|
Text Classification (Q)
|
88% |
591
796.8 IPS |
|
Machine Translation (SP)
|
100% |
466
8.02 IPS |
|
Machine Translation (HP)
|
100% |
460
7.93 IPS |
|
Machine Translation (Q)
|
50% |
353
12.5 IPS |