Upload Date | September 18 2024 02:44 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-X516B |
Model ID | samsung SM-X516B |
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 | 7.26 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
413
76.8 IPS |
|
Image Classification (HP)
|
100% |
409
76.0 IPS |
|
Image Classification (Q)
|
100% |
1307
243.0 IPS |
|
Image Segmentation (SP)
|
100% |
492
7.97 IPS |
|
Image Segmentation (HP)
|
100% |
382
6.19 IPS |
|
Image Segmentation (Q)
|
98% |
1156
18.8 IPS |
|
Pose Estimation (SP)
|
100% |
1728
2.02 IPS |
|
Pose Estimation (HP)
|
100% |
1650
1.93 IPS |
|
Pose Estimation (Q)
|
84% |
3032
3.60 IPS |
|
Object Detection (SP)
|
100% |
309
24.5 IPS |
|
Object Detection (HP)
|
100% |
341
27.0 IPS |
|
Object Detection (Q)
|
83% |
1081
87.3 IPS |
|
Face Detection (SP)
|
100% |
1060
12.6 IPS |
|
Face Detection (HP)
|
100% |
878
10.4 IPS |
|
Face Detection (Q)
|
95% |
2618
31.3 IPS |
|
Depth Estimation (SP)
|
100% |
1247
9.60 IPS |
|
Depth Estimation (HP)
|
99% |
1278
9.85 IPS |
|
Depth Estimation (Q)
|
64% |
2390
21.9 IPS |
|
Style Transfer (SP)
|
89% |
2730
3.54 IPS |
|
Style Transfer (HP)
|
89% |
2962
3.85 IPS |
|
Style Transfer (Q)
|
98% |
6710
8.65 IPS |
|
Image Super-Resolution (SP)
|
100% |
671
24.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
764
28.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
1435
53.2 IPS |
|
Text Classification (SP)
|
100% |
346
462.2 IPS |
|
Text Classification (HP)
|
100% |
338
450.9 IPS |
|
Text Classification (Q)
|
88% |
726
979.0 IPS |
|
Machine Translation (SP)
|
100% |
562
9.68 IPS |
|
Machine Translation (HP)
|
100% |
536
9.22 IPS |
|
Machine Translation (Q)
|
50% |
309
11.0 IPS |