Upload Date | September 18 2024 08:37 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
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% |
130
24.2 IPS |
|
Image Classification (HP)
|
100% |
11625
2.16 KIPS |
|
Image Classification (Q)
|
97% |
26714
4.99 KIPS |
|
Image Segmentation (SP)
|
100% |
167
2.71 IPS |
|
Image Segmentation (HP)
|
100% |
7279
118.0 IPS |
|
Image Segmentation (Q)
|
98% |
19123
311.0 IPS |
|
Pose Estimation (SP)
|
100% |
238
0.28 IPS |
|
Pose Estimation (HP)
|
100% |
57648
67.3 IPS |
|
Pose Estimation (Q)
|
98% |
272507
319.0 IPS |
|
Object Detection (SP)
|
100% |
130
10.3 IPS |
|
Object Detection (HP)
|
100% |
10714
849.8 IPS |
|
Object Detection (Q)
|
86% |
11859
953.6 IPS |
|
Face Detection (SP)
|
100% |
326
3.88 IPS |
|
Face Detection (HP)
|
100% |
22263
264.5 IPS |
|
Face Detection (Q)
|
97% |
70027
835.1 IPS |
|
Depth Estimation (SP)
|
100% |
290
2.24 IPS |
|
Depth Estimation (HP)
|
99% |
40813
314.4 IPS |
|
Depth Estimation (Q)
|
63% |
74694
699.4 IPS |
|
Style Transfer (SP)
|
100% |
487
0.63 IPS |
|
Style Transfer (HP)
|
24% |
2858
86.4 IPS |
|
Style Transfer (Q)
|
98% |
218541
281.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
147
5.43 IPS |
|
Image Super-Resolution (HP)
|
100% |
29443
1.09 KIPS |
|
Image Super-Resolution (Q)
|
97% |
75584
2.80 KIPS |
|
Text Classification (SP)
|
100% |
188
250.5 IPS |
|
Text Classification (HP)
|
100% |
2337
3.12 KIPS |
|
Text Classification (Q)
|
93% |
4866
6.53 KIPS |
|
Machine Translation (SP)
|
100% |
314
5.41 IPS |
|
Machine Translation (HP)
|
100% |
2611
45.0 IPS |
|
Machine Translation (Q)
|
30% |
178
35.7 IPS |