User | Maximum_Game |
Upload Date | February 27 2025 07:11 PM |
Views | 2 |
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% |
147
27.4 IPS |
|
Image Classification (Q)
|
99% |
346
64.5 IPS |
|
Image Segmentation (SP)
|
100% |
194
3.14 IPS |
|
Image Segmentation (HP)
|
100% |
196
3.18 IPS |
|
Image Segmentation (Q)
|
98% |
350
5.69 IPS |
|
Pose Estimation (SP)
|
100% |
261
0.30 IPS |
|
Pose Estimation (HP)
|
100% |
261
0.30 IPS |
|
Pose Estimation (Q)
|
98% |
983
1.15 IPS |
|
Object Detection (SP)
|
100% |
146
11.6 IPS |
|
Object Detection (HP)
|
100% |
147
11.7 IPS |
|
Object Detection (Q)
|
87% |
393
31.5 IPS |
|
Face Detection (SP)
|
100% |
359
4.27 IPS |
|
Face Detection (HP)
|
100% |
363
4.31 IPS |
|
Face Detection (Q)
|
97% |
734
8.76 IPS |
|
Depth Estimation (SP)
|
100% |
306
2.35 IPS |
|
Depth Estimation (HP)
|
99% |
307
2.37 IPS |
|
Depth Estimation (Q)
|
64% |
714
6.48 IPS |
|
Style Transfer (SP)
|
100% |
502
0.65 IPS |
|
Style Transfer (HP)
|
100% |
502
0.65 IPS |
|
Style Transfer (Q)
|
98% |
1491
1.92 IPS |
|
Image Super-Resolution (SP)
|
100% |
153
5.64 IPS |
|
Image Super-Resolution (HP)
|
100% |
152
5.63 IPS |
|
Image Super-Resolution (Q)
|
97% |
563
20.9 IPS |
|
Text Classification (SP)
|
100% |
221
295.4 IPS |
|
Text Classification (HP)
|
100% |
221
294.5 IPS |
|
Text Classification (Q)
|
91% |
342
460.3 IPS |
|
Machine Translation (SP)
|
100% |
350
6.02 IPS |
|
Machine Translation (HP)
|
100% |
362
6.23 IPS |
|
Machine Translation (Q)
|
57% |
276
6.75 IPS |