User | funskeen |
Upload Date | February 17 2025 09:09 PM |
Views | 8 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A556E |
Model ID | samsung SM-A556E |
Motherboard | s5e8845 |
Governor | energy_aware |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 2 |
Base Frequency | 2.05 GHz |
Cluster 1 | 4 Cores @ 2.05 GHz |
Cluster 2 | 4 Cores @ 2.75 GHz |
Memory Information | |
---|---|
Size | 7.26 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
222
41.3 IPS |
|
Image Classification (HP)
|
100% |
202
37.6 IPS |
|
Image Classification (Q)
|
99% |
186
34.8 IPS |
|
Image Segmentation (SP)
|
100% |
457
7.41 IPS |
|
Image Segmentation (HP)
|
100% |
614
9.96 IPS |
|
Image Segmentation (Q)
|
98% |
581
9.44 IPS |
|
Pose Estimation (SP)
|
100% |
384
0.45 IPS |
|
Pose Estimation (HP)
|
100% |
544
0.63 IPS |
|
Pose Estimation (Q)
|
96% |
527
0.62 IPS |
|
Object Detection (SP)
|
100% |
225
17.9 IPS |
|
Object Detection (HP)
|
100% |
249
19.8 IPS |
|
Object Detection (Q)
|
86% |
271
21.8 IPS |
|
Face Detection (SP)
|
100% |
875
10.4 IPS |
|
Face Detection (HP)
|
100% |
1045
12.4 IPS |
|
Face Detection (Q)
|
97% |
991
11.8 IPS |
|
Depth Estimation (SP)
|
100% |
673
5.19 IPS |
|
Depth Estimation (HP)
|
99% |
918
7.09 IPS |
|
Depth Estimation (Q)
|
63% |
732
6.84 IPS |
|
Style Transfer (SP)
|
100% |
1949
2.51 IPS |
|
Style Transfer (HP)
|
100% |
2152
2.77 IPS |
|
Style Transfer (Q)
|
98% |
2152
2.77 IPS |
|
Image Super-Resolution (SP)
|
100% |
324
12.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
421
15.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
410
15.2 IPS |
|
Text Classification (SP)
|
100% |
128
171.4 IPS |
|
Text Classification (HP)
|
100% |
129
172.0 IPS |
|
Text Classification (Q)
|
91% |
317
426.0 IPS |
|
Machine Translation (SP)
|
100% |
226
3.90 IPS |
|
Machine Translation (HP)
|
100% |
227
3.92 IPS |
|
Machine Translation (Q)
|
57% |
282
6.89 IPS |