Upload Date | March 29 2025 04:32 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-M346B1 |
Model ID | samsung SM-M346B1 |
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% |
240
44.7 IPS |
|
Image Classification (HP)
|
100% |
241
44.9 IPS |
|
Image Classification (Q)
|
100% |
772
143.5 IPS |
|
Image Segmentation (SP)
|
100% |
297
4.82 IPS |
|
Image Segmentation (HP)
|
100% |
305
4.95 IPS |
|
Image Segmentation (Q)
|
98% |
864
14.0 IPS |
|
Pose Estimation (SP)
|
100% |
1145
1.34 IPS |
|
Pose Estimation (HP)
|
100% |
1153
1.35 IPS |
|
Pose Estimation (Q)
|
84% |
1783
2.11 IPS |
|
Object Detection (SP)
|
100% |
229
18.2 IPS |
|
Object Detection (HP)
|
100% |
230
18.3 IPS |
|
Object Detection (Q)
|
83% |
724
58.5 IPS |
|
Face Detection (SP)
|
100% |
727
8.64 IPS |
|
Face Detection (HP)
|
100% |
736
8.74 IPS |
|
Face Detection (Q)
|
95% |
1741
20.8 IPS |
|
Depth Estimation (SP)
|
100% |
856
6.60 IPS |
|
Depth Estimation (HP)
|
99% |
969
7.46 IPS |
|
Depth Estimation (Q)
|
64% |
1696
15.5 IPS |
|
Style Transfer (SP)
|
89% |
1929
2.50 IPS |
|
Style Transfer (HP)
|
89% |
1913
2.48 IPS |
|
Style Transfer (Q)
|
98% |
4137
5.33 IPS |
|
Image Super-Resolution (SP)
|
100% |
459
16.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
455
16.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
1027
38.1 IPS |
|
Text Classification (SP)
|
100% |
298
398.1 IPS |
|
Text Classification (HP)
|
100% |
297
396.3 IPS |
|
Text Classification (Q)
|
88% |
614
828.3 IPS |
|
Machine Translation (SP)
|
100% |
470
8.09 IPS |
|
Machine Translation (HP)
|
100% |
463
7.98 IPS |
|
Machine Translation (Q)
|
50% |
361
12.8 IPS |