Upload Date | December 21 2024 09:37 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 8 Gen 2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy S23 Plus |
Model ID | samsung SM-S916B |
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 | 6.89 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
986
183.4 IPS |
|
Image Classification (HP)
|
100% |
667
124.0 IPS |
|
Image Classification (Q)
|
100% |
1514
281.5 IPS |
|
Image Segmentation (SP)
|
100% |
691
11.2 IPS |
|
Image Segmentation (HP)
|
100% |
652
10.6 IPS |
|
Image Segmentation (Q)
|
98% |
1690
27.5 IPS |
|
Pose Estimation (SP)
|
100% |
1949
2.27 IPS |
|
Pose Estimation (HP)
|
100% |
1479
1.73 IPS |
|
Pose Estimation (Q)
|
84% |
2855
3.39 IPS |
|
Object Detection (SP)
|
98% |
563
44.8 IPS |
|
Object Detection (HP)
|
98% |
561
44.6 IPS |
|
Object Detection (Q)
|
83% |
803
64.8 IPS |
|
Face Detection (SP)
|
100% |
689
8.18 IPS |
|
Face Detection (HP)
|
100% |
996
11.8 IPS |
|
Face Detection (Q)
|
95% |
2136
25.5 IPS |
|
Depth Estimation (SP)
|
99% |
1160
8.97 IPS |
|
Depth Estimation (HP)
|
99% |
1403
10.8 IPS |
|
Depth Estimation (Q)
|
64% |
1766
16.2 IPS |
|
Style Transfer (SP)
|
89% |
2985
3.88 IPS |
|
Style Transfer (HP)
|
89% |
1996
2.59 IPS |
|
Style Transfer (Q)
|
98% |
5253
6.77 IPS |
|
Image Super-Resolution (SP)
|
100% |
677
25.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
773
28.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
1182
43.8 IPS |
|
Text Classification (SP)
|
100% |
348
464.2 IPS |
|
Text Classification (HP)
|
99% |
318
424.9 IPS |
|
Text Classification (Q)
|
88% |
591
797.2 IPS |
|
Machine Translation (SP)
|
100% |
714
12.3 IPS |
|
Machine Translation (HP)
|
100% |
661
11.4 IPS |
|
Machine Translation (Q)
|
50% |
358
12.7 IPS |