User | Masatako123 |
Upload Date | December 01 2024 02:25 PM |
Views | 9 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | ARM SM8350 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SCG09 |
Model ID | samsung SCG09 |
Motherboard | lahaina |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM SM8350 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 7.19 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
82
15.2 IPS |
|
Image Classification (HP)
|
100% |
87
16.2 IPS |
|
Image Classification (Q)
|
99% |
9848
1.84 KIPS |
|
Image Segmentation (SP)
|
100% |
113
1.82 IPS |
|
Image Segmentation (HP)
|
100% |
114
1.84 IPS |
|
Image Segmentation (Q)
|
98% |
9509
154.6 IPS |
|
Pose Estimation (SP)
|
100% |
146
0.17 IPS |
|
Pose Estimation (HP)
|
100% |
147
0.17 IPS |
|
Pose Estimation (Q)
|
94% |
97763
114.6 IPS |
|
Object Detection (SP)
|
100% |
86
6.82 IPS |
|
Object Detection (HP)
|
100% |
87
6.87 IPS |
|
Object Detection (Q)
|
88% |
5650
452.6 IPS |
|
Face Detection (SP)
|
100% |
218
2.59 IPS |
|
Face Detection (HP)
|
100% |
223
2.65 IPS |
|
Face Detection (Q)
|
97% |
26788
319.4 IPS |
|
Depth Estimation (SP)
|
100% |
184
1.41 IPS |
|
Depth Estimation (HP)
|
99% |
189
1.45 IPS |
|
Depth Estimation (Q)
|
64% |
34447
317.1 IPS |
|
Style Transfer (SP)
|
100% |
318
0.41 IPS |
|
Style Transfer (HP)
|
100% |
305
0.39 IPS |
|
Style Transfer (Q)
|
98% |
94753
122.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
89
3.27 IPS |
|
Image Super-Resolution (HP)
|
100% |
91
3.36 IPS |
|
Image Super-Resolution (Q)
|
97% |
30469
1.13 KIPS |
|
Text Classification (SP)
|
100% |
122
163.5 IPS |
|
Text Classification (HP)
|
100% |
162
216.0 IPS |
|
Text Classification (Q)
|
94% |
2209
2.96 KIPS |
|
Machine Translation (SP)
|
100% |
208
3.58 IPS |
|
Machine Translation (HP)
|
100% |
202
3.48 IPS |
|
Machine Translation (Q)
|
37% |
186
18.8 IPS |