Upload Date | June 12 2025 03:58 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Snapdragon 8 Gen 2 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Samsung Galaxy S23 |
Model ID | samsung SM-S911B |
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 | 6.91 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
667
124.1 IPS |
|
Image Classification (HP)
|
100% |
1085
201.7 IPS |
|
Image Classification (Q)
|
96% |
812
151.6 IPS |
|
Image Segmentation (SP)
|
100% |
1097
17.8 IPS |
|
Image Segmentation (HP)
|
100% |
1211
19.6 IPS |
|
Image Segmentation (Q)
|
98% |
1060
17.2 IPS |
|
Pose Estimation (SP)
|
100% |
975
1.14 IPS |
|
Pose Estimation (HP)
|
100% |
1433
1.67 IPS |
|
Pose Estimation (Q)
|
96% |
1428
1.67 IPS |
|
Object Detection (SP)
|
100% |
497
39.4 IPS |
|
Object Detection (HP)
|
100% |
744
59.0 IPS |
|
Object Detection (Q)
|
87% |
828
66.5 IPS |
|
Face Detection (SP)
|
100% |
2217
26.3 IPS |
|
Face Detection (HP)
|
100% |
2986
35.5 IPS |
|
Face Detection (Q)
|
97% |
2540
30.3 IPS |
|
Depth Estimation (SP)
|
100% |
1500
11.6 IPS |
|
Depth Estimation (HP)
|
99% |
2864
22.1 IPS |
|
Depth Estimation (Q)
|
63% |
2360
21.9 IPS |
|
Style Transfer (SP)
|
100% |
3859
4.96 IPS |
|
Style Transfer (HP)
|
100% |
8687
11.2 IPS |
|
Style Transfer (Q)
|
98% |
8630
11.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
454
16.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
376
13.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
377
14.0 IPS |
|
Text Classification (SP)
|
100% |
407
543.2 IPS |
|
Text Classification (HP)
|
100% |
421
561.9 IPS |
|
Text Classification (Q)
|
91% |
642
863.2 IPS |
|
Machine Translation (SP)
|
100% |
627
10.8 IPS |
|
Machine Translation (HP)
|
100% |
624
10.8 IPS |
|
Machine Translation (Q)
|
57% |
486
11.9 IPS |