User | Maximum_Game |
Upload Date | February 28 2025 01:45 AM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | Qualcomm Snapdragon 855 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Samsung Galaxy S10+ |
Model ID | samsung SM-G975U1 |
Motherboard | msmnile |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 13 part 2052 revision 14 |
Base Frequency | 1.78 GHz |
Cluster 1 | 4 Cores @ 1.79 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 11.17 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
147
27.4 IPS |
|
Image Classification (HP)
|
100% |
149
27.7 IPS |
|
Image Classification (Q)
|
99% |
346
64.5 IPS |
|
Image Segmentation (SP)
|
100% |
193
3.13 IPS |
|
Image Segmentation (HP)
|
100% |
195
3.16 IPS |
|
Image Segmentation (Q)
|
98% |
350
5.68 IPS |
|
Pose Estimation (SP)
|
100% |
249
0.29 IPS |
|
Pose Estimation (HP)
|
100% |
247
0.29 IPS |
|
Pose Estimation (Q)
|
98% |
689
0.81 IPS |
|
Object Detection (SP)
|
100% |
106
8.39 IPS |
|
Object Detection (HP)
|
100% |
147
11.7 IPS |
|
Object Detection (Q)
|
87% |
393
31.5 IPS |
|
Face Detection (SP)
|
100% |
357
4.24 IPS |
|
Face Detection (HP)
|
100% |
361
4.29 IPS |
|
Face Detection (Q)
|
97% |
734
8.75 IPS |
|
Depth Estimation (SP)
|
100% |
300
2.31 IPS |
|
Depth Estimation (HP)
|
99% |
289
2.23 IPS |
|
Depth Estimation (Q)
|
64% |
581
5.28 IPS |
|
Style Transfer (SP)
|
100% |
374
0.48 IPS |
|
Style Transfer (HP)
|
100% |
496
0.64 IPS |
|
Style Transfer (Q)
|
98% |
1399
1.80 IPS |
|
Image Super-Resolution (SP)
|
100% |
131
4.83 IPS |
|
Image Super-Resolution (HP)
|
100% |
114
4.20 IPS |
|
Image Super-Resolution (Q)
|
97% |
398
14.8 IPS |
|
Text Classification (SP)
|
100% |
156
208.7 IPS |
|
Text Classification (HP)
|
100% |
156
208.0 IPS |
|
Text Classification (Q)
|
91% |
242
325.9 IPS |
|
Machine Translation (SP)
|
100% |
261
4.49 IPS |
|
Machine Translation (HP)
|
100% |
267
4.61 IPS |
|
Machine Translation (Q)
|
57% |
193
4.73 IPS |