Upload Date | December 24 2024 01:06 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 8 Gen 2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy Tab S9 |
Model ID | samsung SM-X710 |
Motherboard | kalama |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
Base Frequency | 2.02 GHz |
Cluster 1 | 3 Cores @ 2.02 GHz |
Cluster 2 | 4 Cores @ 2.80 GHz |
Cluster 3 | 1 Core @ 3.36 GHz |
Memory Information | |
---|---|
Size | 7.03 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
926
172.2 IPS |
|
Image Classification (HP)
|
100% |
682
126.8 IPS |
|
Image Classification (Q)
|
100% |
1227
228.2 IPS |
|
Image Segmentation (SP)
|
100% |
442
7.16 IPS |
|
Image Segmentation (HP)
|
100% |
440
7.13 IPS |
|
Image Segmentation (Q)
|
98% |
1548
25.2 IPS |
|
Pose Estimation (SP)
|
100% |
2024
2.36 IPS |
|
Pose Estimation (HP)
|
100% |
1900
2.22 IPS |
|
Pose Estimation (Q)
|
84% |
3718
4.41 IPS |
|
Object Detection (SP)
|
98% |
356
28.4 IPS |
|
Object Detection (HP)
|
98% |
560
44.6 IPS |
|
Object Detection (Q)
|
83% |
1034
83.5 IPS |
|
Face Detection (SP)
|
100% |
1003
11.9 IPS |
|
Face Detection (HP)
|
100% |
1208
14.4 IPS |
|
Face Detection (Q)
|
95% |
2141
25.6 IPS |
|
Depth Estimation (SP)
|
99% |
1114
8.61 IPS |
|
Depth Estimation (HP)
|
99% |
1099
8.49 IPS |
|
Depth Estimation (Q)
|
64% |
2722
24.9 IPS |
|
Style Transfer (SP)
|
89% |
3442
4.47 IPS |
|
Style Transfer (HP)
|
89% |
3458
4.49 IPS |
|
Style Transfer (Q)
|
98% |
5229
6.74 IPS |
|
Image Super-Resolution (SP)
|
100% |
547
20.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
560
20.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
1202
44.6 IPS |
|
Text Classification (SP)
|
100% |
356
474.7 IPS |
|
Text Classification (HP)
|
99% |
311
414.8 IPS |
|
Text Classification (Q)
|
88% |
491
661.7 IPS |
|
Machine Translation (SP)
|
100% |
767
13.2 IPS |
|
Machine Translation (HP)
|
100% |
668
11.5 IPS |
|
Machine Translation (Q)
|
50% |
345
12.2 IPS |