Upload Date | December 25 2024 10:48 PM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A256E |
Model ID | samsung SM-A256E |
Motherboard | s5e8825 |
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 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 5.26 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
236
44.0 IPS |
|
Image Classification (HP)
|
100% |
238
44.3 IPS |
|
Image Classification (Q)
|
100% |
733
136.3 IPS |
|
Image Segmentation (SP)
|
100% |
298
4.84 IPS |
|
Image Segmentation (HP)
|
100% |
298
4.83 IPS |
|
Image Segmentation (Q)
|
98% |
851
13.8 IPS |
|
Pose Estimation (SP)
|
100% |
1135
1.32 IPS |
|
Pose Estimation (HP)
|
100% |
1136
1.33 IPS |
|
Pose Estimation (Q)
|
84% |
1737
2.06 IPS |
|
Object Detection (SP)
|
100% |
225
17.8 IPS |
|
Object Detection (HP)
|
100% |
226
17.9 IPS |
|
Object Detection (Q)
|
83% |
721
58.2 IPS |
|
Face Detection (SP)
|
100% |
743
8.82 IPS |
|
Face Detection (HP)
|
100% |
743
8.82 IPS |
|
Face Detection (Q)
|
95% |
1751
20.9 IPS |
|
Depth Estimation (SP)
|
100% |
968
7.46 IPS |
|
Depth Estimation (HP)
|
99% |
930
7.16 IPS |
|
Depth Estimation (Q)
|
64% |
1691
15.5 IPS |
|
Style Transfer (SP)
|
89% |
1937
2.51 IPS |
|
Style Transfer (HP)
|
89% |
1944
2.52 IPS |
|
Style Transfer (Q)
|
98% |
4158
5.36 IPS |
|
Image Super-Resolution (SP)
|
100% |
512
18.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
512
18.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
1029
38.1 IPS |
|
Text Classification (SP)
|
100% |
298
397.1 IPS |
|
Text Classification (HP)
|
100% |
294
392.2 IPS |
|
Text Classification (Q)
|
88% |
604
814.6 IPS |
|
Machine Translation (SP)
|
100% |
473
8.15 IPS |
|
Machine Translation (HP)
|
100% |
462
7.96 IPS |
|
Machine Translation (Q)
|
50% |
367
13.0 IPS |