Upload Date | December 26 2024 05:59 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-X610 |
Model ID | samsung SM-X610 |
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 | 11.45 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
455
84.7 IPS |
|
Image Classification (HP)
|
100% |
433
80.6 IPS |
|
Image Classification (Q)
|
100% |
1391
258.6 IPS |
|
Image Segmentation (SP)
|
100% |
515
8.35 IPS |
|
Image Segmentation (HP)
|
100% |
513
8.32 IPS |
|
Image Segmentation (Q)
|
98% |
1641
26.7 IPS |
|
Pose Estimation (SP)
|
100% |
1850
2.16 IPS |
|
Pose Estimation (HP)
|
100% |
1822
2.13 IPS |
|
Pose Estimation (Q)
|
84% |
3357
3.98 IPS |
|
Object Detection (SP)
|
100% |
382
30.3 IPS |
|
Object Detection (HP)
|
100% |
387
30.7 IPS |
|
Object Detection (Q)
|
83% |
1188
96.0 IPS |
|
Face Detection (SP)
|
100% |
1110
13.2 IPS |
|
Face Detection (HP)
|
100% |
1125
13.4 IPS |
|
Face Detection (Q)
|
95% |
3033
36.2 IPS |
|
Depth Estimation (SP)
|
100% |
1566
12.1 IPS |
|
Depth Estimation (HP)
|
99% |
1570
12.1 IPS |
|
Depth Estimation (Q)
|
64% |
3051
27.9 IPS |
|
Style Transfer (SP)
|
89% |
3169
4.11 IPS |
|
Style Transfer (HP)
|
89% |
3123
4.05 IPS |
|
Style Transfer (Q)
|
98% |
7635
9.84 IPS |
|
Image Super-Resolution (SP)
|
100% |
867
32.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
877
32.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
1910
70.8 IPS |
|
Text Classification (SP)
|
100% |
474
632.1 IPS |
|
Text Classification (HP)
|
100% |
470
627.4 IPS |
|
Text Classification (Q)
|
88% |
890
1.20 KIPS |
|
Machine Translation (SP)
|
100% |
616
10.6 IPS |
|
Machine Translation (HP)
|
100% |
604
10.4 IPS |
|
Machine Translation (Q)
|
50% |
376
13.3 IPS |