Upload Date | January 04 2025 03:51 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
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% |
238
44.2 IPS |
|
Image Classification (HP)
|
100% |
237
44.1 IPS |
|
Image Classification (Q)
|
100% |
715
133.0 IPS |
|
Image Segmentation (SP)
|
100% |
313
5.07 IPS |
|
Image Segmentation (HP)
|
100% |
312
5.05 IPS |
|
Image Segmentation (Q)
|
98% |
826
13.4 IPS |
|
Pose Estimation (SP)
|
100% |
1180
1.38 IPS |
|
Pose Estimation (HP)
|
100% |
1157
1.35 IPS |
|
Pose Estimation (Q)
|
84% |
1736
2.06 IPS |
|
Object Detection (SP)
|
100% |
232
18.4 IPS |
|
Object Detection (HP)
|
100% |
234
18.6 IPS |
|
Object Detection (Q)
|
83% |
716
57.8 IPS |
|
Face Detection (SP)
|
100% |
768
9.12 IPS |
|
Face Detection (HP)
|
100% |
766
9.10 IPS |
|
Face Detection (Q)
|
95% |
1719
20.5 IPS |
|
Depth Estimation (SP)
|
100% |
1016
7.83 IPS |
|
Depth Estimation (HP)
|
99% |
1018
7.85 IPS |
|
Depth Estimation (Q)
|
64% |
1619
14.8 IPS |
|
Style Transfer (SP)
|
89% |
1963
2.55 IPS |
|
Style Transfer (HP)
|
89% |
1954
2.54 IPS |
|
Style Transfer (Q)
|
98% |
4007
5.17 IPS |
|
Image Super-Resolution (SP)
|
100% |
546
20.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
542
20.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
1006
37.3 IPS |
|
Text Classification (SP)
|
100% |
294
392.4 IPS |
|
Text Classification (HP)
|
100% |
290
386.8 IPS |
|
Text Classification (Q)
|
88% |
581
783.7 IPS |
|
Machine Translation (SP)
|
100% |
491
8.46 IPS |
|
Machine Translation (HP)
|
100% |
485
8.36 IPS |
|
Machine Translation (Q)
|
50% |
373
13.2 IPS |