Upload Date | January 06 2025 09:01 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 8 Gen 2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy S23 Ultra |
Model ID | samsung SM-S918N |
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 | 10.77 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
681
126.6 IPS |
|
Image Classification (HP)
|
100% |
690
128.3 IPS |
|
Image Classification (Q)
|
100% |
1082
201.3 IPS |
|
Image Segmentation (SP)
|
100% |
756
12.3 IPS |
|
Image Segmentation (HP)
|
100% |
437
7.08 IPS |
|
Image Segmentation (Q)
|
98% |
1215
19.8 IPS |
|
Pose Estimation (SP)
|
100% |
1780
2.08 IPS |
|
Pose Estimation (HP)
|
100% |
1255
1.46 IPS |
|
Pose Estimation (Q)
|
84% |
2215
2.63 IPS |
|
Object Detection (SP)
|
98% |
558
44.4 IPS |
|
Object Detection (HP)
|
98% |
529
42.1 IPS |
|
Object Detection (Q)
|
83% |
792
64.0 IPS |
|
Face Detection (SP)
|
100% |
983
11.7 IPS |
|
Face Detection (HP)
|
100% |
985
11.7 IPS |
|
Face Detection (Q)
|
95% |
1639
19.6 IPS |
|
Depth Estimation (SP)
|
99% |
1312
10.1 IPS |
|
Depth Estimation (HP)
|
99% |
1311
10.1 IPS |
|
Depth Estimation (Q)
|
64% |
2009
18.4 IPS |
|
Style Transfer (SP)
|
89% |
2855
3.71 IPS |
|
Style Transfer (HP)
|
89% |
2922
3.79 IPS |
|
Style Transfer (Q)
|
98% |
5185
6.69 IPS |
|
Image Super-Resolution (SP)
|
100% |
535
19.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
669
24.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
1474
54.6 IPS |
|
Text Classification (SP)
|
100% |
348
464.0 IPS |
|
Text Classification (HP)
|
99% |
252
336.9 IPS |
|
Text Classification (Q)
|
88% |
730
985.0 IPS |
|
Machine Translation (SP)
|
100% |
709
12.2 IPS |
|
Machine Translation (HP)
|
100% |
656
11.3 IPS |
|
Machine Translation (Q)
|
50% |
337
12.0 IPS |