Upload Date | December 26 2024 01:13 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A336B |
Model ID | samsung SM-A336B |
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% |
241
44.7 IPS |
|
Image Classification (HP)
|
100% |
240
44.6 IPS |
|
Image Classification (Q)
|
100% |
773
143.7 IPS |
|
Image Segmentation (SP)
|
100% |
307
4.98 IPS |
|
Image Segmentation (HP)
|
100% |
306
4.97 IPS |
|
Image Segmentation (Q)
|
98% |
870
14.2 IPS |
|
Pose Estimation (SP)
|
100% |
1145
1.34 IPS |
|
Pose Estimation (HP)
|
100% |
1085
1.27 IPS |
|
Pose Estimation (Q)
|
84% |
1801
2.14 IPS |
|
Object Detection (SP)
|
100% |
225
17.9 IPS |
|
Object Detection (HP)
|
100% |
227
18.0 IPS |
|
Object Detection (Q)
|
83% |
721
58.2 IPS |
|
Face Detection (SP)
|
100% |
711
8.45 IPS |
|
Face Detection (HP)
|
100% |
709
8.43 IPS |
|
Face Detection (Q)
|
95% |
1739
20.8 IPS |
|
Depth Estimation (SP)
|
100% |
894
6.89 IPS |
|
Depth Estimation (HP)
|
99% |
863
6.65 IPS |
|
Depth Estimation (Q)
|
64% |
1703
15.6 IPS |
|
Style Transfer (SP)
|
89% |
1883
2.44 IPS |
|
Style Transfer (HP)
|
89% |
1868
2.43 IPS |
|
Style Transfer (Q)
|
98% |
4153
5.35 IPS |
|
Image Super-Resolution (SP)
|
100% |
443
16.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
448
16.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
1030
38.2 IPS |
|
Text Classification (SP)
|
100% |
297
396.3 IPS |
|
Text Classification (HP)
|
100% |
294
392.5 IPS |
|
Text Classification (Q)
|
88% |
610
822.8 IPS |
|
Machine Translation (SP)
|
100% |
457
7.87 IPS |
|
Machine Translation (HP)
|
100% |
446
7.68 IPS |
|
Machine Translation (Q)
|
50% |
362
12.9 IPS |