Upload Date | October 19 2024 01:15 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Snapdragon 8 Gen 2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy S23 Ultra |
Model ID | samsung SM-S918B |
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% |
610
113.4 IPS |
|
Image Classification (HP)
|
100% |
1073
199.6 IPS |
|
Image Classification (Q)
|
96% |
805
150.3 IPS |
|
Image Segmentation (SP)
|
100% |
1310
21.2 IPS |
|
Image Segmentation (HP)
|
100% |
1989
32.2 IPS |
|
Image Segmentation (Q)
|
98% |
1059
17.2 IPS |
|
Pose Estimation (SP)
|
100% |
974
1.14 IPS |
|
Pose Estimation (HP)
|
100% |
1434
1.67 IPS |
|
Pose Estimation (Q)
|
96% |
1431
1.68 IPS |
|
Object Detection (SP)
|
100% |
492
39.0 IPS |
|
Object Detection (HP)
|
100% |
844
67.0 IPS |
|
Object Detection (Q)
|
87% |
858
68.9 IPS |
|
Face Detection (SP)
|
100% |
2188
26.0 IPS |
|
Face Detection (HP)
|
100% |
3325
39.5 IPS |
|
Face Detection (Q)
|
97% |
2557
30.5 IPS |
|
Depth Estimation (SP)
|
100% |
1514
11.7 IPS |
|
Depth Estimation (HP)
|
99% |
2869
22.2 IPS |
|
Depth Estimation (Q)
|
63% |
2379
22.1 IPS |
|
Style Transfer (SP)
|
100% |
3862
4.96 IPS |
|
Style Transfer (HP)
|
100% |
8676
11.2 IPS |
|
Style Transfer (Q)
|
98% |
8606
11.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
440
16.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
372
13.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
368
13.6 IPS |
|
Text Classification (SP)
|
100% |
439
586.1 IPS |
|
Text Classification (HP)
|
100% |
439
585.5 IPS |
|
Text Classification (Q)
|
91% |
685
921.4 IPS |
|
Machine Translation (SP)
|
100% |
654
11.3 IPS |
|
Machine Translation (HP)
|
100% |
646
11.1 IPS |
|
Machine Translation (Q)
|
57% |
494
12.1 IPS |