User | inc7007 |
Upload Date | January 18 2025 09:10 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT6877V/TTZA |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A346B |
Model ID | samsung SM-A346B |
Motherboard | a34x |
CPU Information | |
---|---|
Name | ARM MT6877V/TTZA |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.60 GHz |
Memory Information | |
---|---|
Size | 7.31 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
287
53.4 IPS |
|
Image Classification (HP)
|
100% |
286
53.2 IPS |
|
Image Classification (Q)
|
100% |
846
157.3 IPS |
|
Image Segmentation (SP)
|
100% |
357
5.79 IPS |
|
Image Segmentation (HP)
|
100% |
358
5.80 IPS |
|
Image Segmentation (Q)
|
98% |
975
15.9 IPS |
|
Pose Estimation (SP)
|
100% |
1182
1.38 IPS |
|
Pose Estimation (HP)
|
100% |
1069
1.25 IPS |
|
Pose Estimation (Q)
|
84% |
1665
1.97 IPS |
|
Object Detection (SP)
|
100% |
223
17.7 IPS |
|
Object Detection (HP)
|
100% |
214
17.0 IPS |
|
Object Detection (Q)
|
83% |
638
51.6 IPS |
|
Face Detection (SP)
|
100% |
746
8.87 IPS |
|
Face Detection (HP)
|
100% |
740
8.79 IPS |
|
Face Detection (Q)
|
95% |
1478
17.6 IPS |
|
Depth Estimation (SP)
|
100% |
902
6.95 IPS |
|
Depth Estimation (HP)
|
99% |
911
7.02 IPS |
|
Depth Estimation (Q)
|
64% |
1371
12.6 IPS |
|
Style Transfer (SP)
|
89% |
1780
2.31 IPS |
|
Style Transfer (HP)
|
89% |
1695
2.20 IPS |
|
Style Transfer (Q)
|
98% |
3485
4.49 IPS |
|
Image Super-Resolution (SP)
|
100% |
458
16.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
455
16.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
832
30.8 IPS |
|
Text Classification (SP)
|
100% |
235
313.6 IPS |
|
Text Classification (HP)
|
100% |
232
309.4 IPS |
|
Text Classification (Q)
|
88% |
520
701.9 IPS |
|
Machine Translation (SP)
|
100% |
395
6.80 IPS |
|
Machine Translation (HP)
|
100% |
393
6.78 IPS |
|
Machine Translation (Q)
|
50% |
317
11.2 IPS |