User | inc7007 |
Upload Date | February 12 2025 01:17 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% |
285
53.0 IPS |
|
Image Classification (HP)
|
100% |
284
52.8 IPS |
|
Image Classification (Q)
|
100% |
844
157.0 IPS |
|
Image Segmentation (SP)
|
100% |
357
5.79 IPS |
|
Image Segmentation (HP)
|
100% |
355
5.75 IPS |
|
Image Segmentation (Q)
|
98% |
973
15.8 IPS |
|
Pose Estimation (SP)
|
100% |
1386
1.62 IPS |
|
Pose Estimation (HP)
|
100% |
1382
1.61 IPS |
|
Pose Estimation (Q)
|
84% |
2058
2.44 IPS |
|
Object Detection (SP)
|
100% |
280
22.2 IPS |
|
Object Detection (HP)
|
100% |
280
22.2 IPS |
|
Object Detection (Q)
|
83% |
826
66.7 IPS |
|
Face Detection (SP)
|
100% |
874
10.4 IPS |
|
Face Detection (HP)
|
100% |
882
10.5 IPS |
|
Face Detection (Q)
|
95% |
2001
23.9 IPS |
|
Depth Estimation (SP)
|
100% |
1192
9.18 IPS |
|
Depth Estimation (HP)
|
99% |
1166
8.98 IPS |
|
Depth Estimation (Q)
|
64% |
1923
17.6 IPS |
|
Style Transfer (SP)
|
89% |
2344
3.04 IPS |
|
Style Transfer (HP)
|
89% |
2342
3.04 IPS |
|
Style Transfer (Q)
|
98% |
4868
6.28 IPS |
|
Image Super-Resolution (SP)
|
100% |
637
23.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
642
23.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
1169
43.3 IPS |
|
Text Classification (SP)
|
100% |
342
456.5 IPS |
|
Text Classification (HP)
|
100% |
340
453.9 IPS |
|
Text Classification (Q)
|
88% |
710
958.0 IPS |
|
Machine Translation (SP)
|
100% |
551
9.50 IPS |
|
Machine Translation (HP)
|
100% |
547
9.42 IPS |
|
Machine Translation (Q)
|
50% |
421
14.9 IPS |