Upload Date | April 24 2025 11:26 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-X820 |
Model ID | samsung SM-X820 |
Motherboard | gts10pwifi |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3458 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 3 Cores @ 2.85 GHz |
Cluster 3 | 1 Core @ 3.40 GHz |
Memory Information | |
---|---|
Size | 11.26 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
699
130.0 IPS |
|
Image Classification (HP)
|
100% |
707
131.5 IPS |
|
Image Classification (Q)
|
99% |
630
117.6 IPS |
|
Image Segmentation (SP)
|
100% |
1539
24.9 IPS |
|
Image Segmentation (HP)
|
100% |
1688
27.4 IPS |
|
Image Segmentation (Q)
|
98% |
1664
27.1 IPS |
|
Pose Estimation (SP)
|
100% |
793
0.93 IPS |
|
Pose Estimation (HP)
|
100% |
1211
1.41 IPS |
|
Pose Estimation (Q)
|
96% |
1191
1.40 IPS |
|
Object Detection (SP)
|
100% |
629
49.9 IPS |
|
Object Detection (HP)
|
100% |
704
55.8 IPS |
|
Object Detection (Q)
|
83% |
846
68.5 IPS |
|
Face Detection (SP)
|
100% |
2815
33.5 IPS |
|
Face Detection (HP)
|
100% |
2770
32.9 IPS |
|
Face Detection (Q)
|
97% |
2987
35.6 IPS |
|
Depth Estimation (SP)
|
100% |
1641
12.6 IPS |
|
Depth Estimation (HP)
|
99% |
2218
17.1 IPS |
|
Depth Estimation (Q)
|
62% |
1803
17.1 IPS |
|
Style Transfer (SP)
|
100% |
4271
5.49 IPS |
|
Style Transfer (HP)
|
100% |
5519
7.09 IPS |
|
Style Transfer (Q)
|
98% |
5575
7.19 IPS |
|
Image Super-Resolution (SP)
|
100% |
809
29.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
1113
41.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
1073
39.8 IPS |
|
Text Classification (SP)
|
100% |
302
403.2 IPS |
|
Text Classification (HP)
|
100% |
303
404.5 IPS |
|
Text Classification (Q)
|
91% |
771
1.04 KIPS |
|
Machine Translation (SP)
|
100% |
693
11.9 IPS |
|
Machine Translation (HP)
|
100% |
684
11.8 IPS |
|
Machine Translation (Q)
|
57% |
510
12.5 IPS |