Upload Date | September 16 2024 09:18 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-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% |
1828
340.0 IPS |
|
Image Classification (HP)
|
100% |
1794
333.7 IPS |
|
Image Classification (Q)
|
100% |
2739
509.4 IPS |
|
Image Segmentation (SP)
|
100% |
1810
29.3 IPS |
|
Image Segmentation (HP)
|
100% |
1732
28.1 IPS |
|
Image Segmentation (Q)
|
98% |
2453
39.9 IPS |
|
Pose Estimation (SP)
|
100% |
2355
2.75 IPS |
|
Pose Estimation (HP)
|
100% |
2747
3.21 IPS |
|
Pose Estimation (Q)
|
84% |
5868
6.96 IPS |
|
Object Detection (SP)
|
98% |
1586
126.2 IPS |
|
Object Detection (HP)
|
98% |
1580
125.8 IPS |
|
Object Detection (Q)
|
83% |
2190
176.9 IPS |
|
Face Detection (SP)
|
100% |
2848
33.8 IPS |
|
Face Detection (HP)
|
100% |
2610
31.0 IPS |
|
Face Detection (Q)
|
95% |
3841
45.9 IPS |
|
Depth Estimation (SP)
|
99% |
2834
21.9 IPS |
|
Depth Estimation (HP)
|
99% |
2949
22.8 IPS |
|
Depth Estimation (Q)
|
64% |
3115
28.5 IPS |
|
Style Transfer (SP)
|
89% |
6746
8.76 IPS |
|
Style Transfer (HP)
|
89% |
6784
8.81 IPS |
|
Style Transfer (Q)
|
98% |
12941
16.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
1301
48.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
1291
47.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
2869
106.3 IPS |
|
Text Classification (SP)
|
100% |
566
755.2 IPS |
|
Text Classification (HP)
|
99% |
576
769.5 IPS |
|
Text Classification (Q)
|
88% |
892
1.20 KIPS |
|
Machine Translation (SP)
|
100% |
1331
22.9 IPS |
|
Machine Translation (HP)
|
100% |
1313
22.6 IPS |
|
Machine Translation (Q)
|
50% |
605
21.5 IPS |