Upload Date | September 14 2024 04:27 AM |
Views | 2 |
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-S918U |
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% |
1361
253.1 IPS |
|
Image Classification (HP)
|
100% |
1873
348.3 IPS |
|
Image Classification (Q)
|
100% |
2874
534.5 IPS |
|
Image Segmentation (SP)
|
100% |
1985
32.2 IPS |
|
Image Segmentation (HP)
|
100% |
1976
32.0 IPS |
|
Image Segmentation (Q)
|
98% |
3254
52.9 IPS |
|
Pose Estimation (SP)
|
100% |
2623
3.06 IPS |
|
Pose Estimation (HP)
|
100% |
2892
3.38 IPS |
|
Pose Estimation (Q)
|
84% |
6389
7.58 IPS |
|
Object Detection (SP)
|
98% |
1467
116.7 IPS |
|
Object Detection (HP)
|
98% |
1526
121.4 IPS |
|
Object Detection (Q)
|
83% |
2420
195.5 IPS |
|
Face Detection (SP)
|
100% |
3104
36.9 IPS |
|
Face Detection (HP)
|
100% |
3100
36.8 IPS |
|
Face Detection (Q)
|
95% |
5535
66.1 IPS |
|
Depth Estimation (SP)
|
99% |
3057
23.6 IPS |
|
Depth Estimation (HP)
|
99% |
2951
22.8 IPS |
|
Depth Estimation (Q)
|
64% |
5103
46.7 IPS |
|
Style Transfer (SP)
|
89% |
6922
8.99 IPS |
|
Style Transfer (HP)
|
89% |
7000
9.09 IPS |
|
Style Transfer (Q)
|
98% |
13003
16.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
1332
49.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
1328
49.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
3304
122.4 IPS |
|
Text Classification (SP)
|
100% |
618
824.8 IPS |
|
Text Classification (HP)
|
99% |
615
820.9 IPS |
|
Text Classification (Q)
|
88% |
1041
1.40 KIPS |
|
Machine Translation (SP)
|
100% |
1411
24.3 IPS |
|
Machine Translation (HP)
|
100% |
1361
23.4 IPS |
|
Machine Translation (Q)
|
50% |
695
24.7 IPS |