Upload Date | June 18 2025 11:38 AM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-M546B |
Model ID | samsung SM-M546B |
Motherboard | s5e8835 |
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 | 4 Cores @ 2.00 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 7.26 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
306
57.0 IPS |
|
Image Classification (HP)
|
100% |
307
57.0 IPS |
|
Image Classification (Q)
|
100% |
958
178.2 IPS |
|
Image Segmentation (SP)
|
100% |
385
6.24 IPS |
|
Image Segmentation (HP)
|
100% |
365
5.92 IPS |
|
Image Segmentation (Q)
|
98% |
1061
17.2 IPS |
|
Pose Estimation (SP)
|
100% |
1443
1.68 IPS |
|
Pose Estimation (HP)
|
100% |
1464
1.71 IPS |
|
Pose Estimation (Q)
|
84% |
2648
3.14 IPS |
|
Object Detection (SP)
|
100% |
286
22.7 IPS |
|
Object Detection (HP)
|
100% |
286
22.7 IPS |
|
Object Detection (Q)
|
83% |
870
70.3 IPS |
|
Face Detection (SP)
|
100% |
1070
12.7 IPS |
|
Face Detection (HP)
|
100% |
870
10.3 IPS |
|
Face Detection (Q)
|
95% |
2169
25.9 IPS |
|
Depth Estimation (SP)
|
100% |
1199
9.24 IPS |
|
Depth Estimation (HP)
|
99% |
1288
9.92 IPS |
|
Depth Estimation (Q)
|
64% |
2015
18.5 IPS |
|
Style Transfer (SP)
|
89% |
2389
3.10 IPS |
|
Style Transfer (HP)
|
89% |
2464
3.20 IPS |
|
Style Transfer (Q)
|
98% |
5168
6.66 IPS |
|
Image Super-Resolution (SP)
|
100% |
679
25.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
732
27.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
1314
48.7 IPS |
|
Text Classification (SP)
|
100% |
303
404.6 IPS |
|
Text Classification (HP)
|
100% |
302
403.6 IPS |
|
Text Classification (Q)
|
88% |
562
758.4 IPS |
|
Machine Translation (SP)
|
100% |
479
8.25 IPS |
|
Machine Translation (HP)
|
100% |
462
7.96 IPS |
|
Machine Translation (Q)
|
50% |
292
10.3 IPS |