User | inc7007 |
Upload Date | January 18 2025 08:15 PM |
Views | 3 |
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% |
286
53.2 IPS |
|
Image Classification (HP)
|
100% |
287
53.3 IPS |
|
Image Classification (Q)
|
100% |
847
157.5 IPS |
|
Image Segmentation (SP)
|
100% |
356
5.77 IPS |
|
Image Segmentation (HP)
|
100% |
359
5.81 IPS |
|
Image Segmentation (Q)
|
98% |
979
15.9 IPS |
|
Pose Estimation (SP)
|
100% |
1397
1.63 IPS |
|
Pose Estimation (HP)
|
100% |
1387
1.62 IPS |
|
Pose Estimation (Q)
|
84% |
2055
2.44 IPS |
|
Object Detection (SP)
|
100% |
281
22.3 IPS |
|
Object Detection (HP)
|
100% |
280
22.2 IPS |
|
Object Detection (Q)
|
83% |
828
66.9 IPS |
|
Face Detection (SP)
|
100% |
855
10.2 IPS |
|
Face Detection (HP)
|
100% |
868
10.3 IPS |
|
Face Detection (Q)
|
95% |
2005
23.9 IPS |
|
Depth Estimation (SP)
|
100% |
1205
9.28 IPS |
|
Depth Estimation (HP)
|
99% |
1185
9.13 IPS |
|
Depth Estimation (Q)
|
64% |
1931
17.7 IPS |
|
Style Transfer (SP)
|
89% |
2332
3.03 IPS |
|
Style Transfer (HP)
|
89% |
2345
3.04 IPS |
|
Style Transfer (Q)
|
98% |
4871
6.28 IPS |
|
Image Super-Resolution (SP)
|
100% |
644
23.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
645
23.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
1172
43.4 IPS |
|
Text Classification (SP)
|
100% |
340
453.2 IPS |
|
Text Classification (HP)
|
100% |
287
383.5 IPS |
|
Text Classification (Q)
|
88% |
653
880.6 IPS |
|
Machine Translation (SP)
|
100% |
553
9.53 IPS |
|
Machine Translation (HP)
|
100% |
546
9.41 IPS |
|
Machine Translation (Q)
|
50% |
364
12.9 IPS |