Upload Date | December 31 2024 04:46 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A166P |
Model ID | samsung SM-A166P |
Motherboard | a16xm |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 7.32 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
233
43.4 IPS |
|
Image Classification (HP)
|
100% |
231
43.0 IPS |
|
Image Classification (Q)
|
100% |
688
128.0 IPS |
|
Image Segmentation (SP)
|
100% |
280
4.54 IPS |
|
Image Segmentation (HP)
|
100% |
278
4.51 IPS |
|
Image Segmentation (Q)
|
98% |
744
12.1 IPS |
|
Pose Estimation (SP)
|
100% |
1089
1.27 IPS |
|
Pose Estimation (HP)
|
100% |
1086
1.27 IPS |
|
Pose Estimation (Q)
|
84% |
1712
2.03 IPS |
|
Object Detection (SP)
|
100% |
233
18.5 IPS |
|
Object Detection (HP)
|
100% |
232
18.4 IPS |
|
Object Detection (Q)
|
83% |
654
52.8 IPS |
|
Face Detection (SP)
|
100% |
723
8.59 IPS |
|
Face Detection (HP)
|
100% |
726
8.63 IPS |
|
Face Detection (Q)
|
95% |
1602
19.1 IPS |
|
Depth Estimation (SP)
|
100% |
913
7.04 IPS |
|
Depth Estimation (HP)
|
99% |
850
6.55 IPS |
|
Depth Estimation (Q)
|
64% |
1632
14.9 IPS |
|
Style Transfer (SP)
|
89% |
1937
2.51 IPS |
|
Style Transfer (HP)
|
89% |
1912
2.48 IPS |
|
Style Transfer (Q)
|
98% |
4106
5.29 IPS |
|
Image Super-Resolution (SP)
|
100% |
421
15.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
428
15.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
1002
37.1 IPS |
|
Text Classification (SP)
|
100% |
288
384.1 IPS |
|
Text Classification (HP)
|
100% |
286
381.4 IPS |
|
Text Classification (Q)
|
88% |
502
676.9 IPS |
|
Machine Translation (SP)
|
100% |
495
8.52 IPS |
|
Machine Translation (HP)
|
100% |
492
8.48 IPS |
|
Machine Translation (Q)
|
50% |
341
12.1 IPS |