Upload Date | September 16 2024 12:25 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A356N |
Model ID | samsung SM-A356N |
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 | 5.30 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
422
78.5 IPS |
|
Image Classification (HP)
|
100% |
386
71.8 IPS |
|
Image Classification (Q)
|
100% |
1270
236.3 IPS |
|
Image Segmentation (SP)
|
100% |
460
7.46 IPS |
|
Image Segmentation (HP)
|
100% |
454
7.35 IPS |
|
Image Segmentation (Q)
|
98% |
1438
23.4 IPS |
|
Pose Estimation (SP)
|
100% |
1751
2.04 IPS |
|
Pose Estimation (HP)
|
100% |
1519
1.77 IPS |
|
Pose Estimation (Q)
|
84% |
2676
3.17 IPS |
|
Object Detection (SP)
|
100% |
343
27.2 IPS |
|
Object Detection (HP)
|
100% |
348
27.6 IPS |
|
Object Detection (Q)
|
83% |
1041
84.1 IPS |
|
Face Detection (SP)
|
100% |
1048
12.5 IPS |
|
Face Detection (HP)
|
100% |
913
10.9 IPS |
|
Face Detection (Q)
|
95% |
2383
28.4 IPS |
|
Depth Estimation (SP)
|
100% |
1293
9.96 IPS |
|
Depth Estimation (HP)
|
99% |
1290
9.94 IPS |
|
Depth Estimation (Q)
|
64% |
2561
23.5 IPS |
|
Style Transfer (SP)
|
89% |
2919
3.79 IPS |
|
Style Transfer (HP)
|
89% |
2927
3.80 IPS |
|
Style Transfer (Q)
|
98% |
6574
8.48 IPS |
|
Image Super-Resolution (SP)
|
100% |
804
29.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
803
29.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
1557
57.7 IPS |
|
Text Classification (SP)
|
100% |
374
499.8 IPS |
|
Text Classification (HP)
|
100% |
376
501.7 IPS |
|
Text Classification (Q)
|
88% |
711
959.5 IPS |
|
Machine Translation (SP)
|
100% |
592
10.2 IPS |
|
Machine Translation (HP)
|
100% |
571
9.84 IPS |
|
Machine Translation (Q)
|
50% |
324
11.5 IPS |