Upload Date | December 27 2024 08:32 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm SM8750 |
System Information | |
---|---|
Operating System | Android 15 |
Model | HONOR PTP-N49 |
Model ID | HONOR PTP-N49 |
Motherboard | PTP |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm SM8750 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 3 part 1 revision 4 |
Base Frequency | 3.53 GHz |
Cluster 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.32 GHz |
Memory Information | |
---|---|
Size | 10.94 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1743
324.2 IPS |
|
Image Classification (HP)
|
100% |
1739
323.4 IPS |
|
Image Classification (Q)
|
100% |
1495
278.0 IPS |
|
Image Segmentation (SP)
|
100% |
1030
16.7 IPS |
|
Image Segmentation (HP)
|
100% |
1031
16.7 IPS |
|
Image Segmentation (Q)
|
98% |
2225
36.2 IPS |
|
Pose Estimation (SP)
|
100% |
2457
2.87 IPS |
|
Pose Estimation (HP)
|
100% |
2488
2.90 IPS |
|
Pose Estimation (Q)
|
84% |
6213
7.37 IPS |
|
Object Detection (SP)
|
98% |
683
54.3 IPS |
|
Object Detection (HP)
|
98% |
694
55.2 IPS |
|
Object Detection (Q)
|
83% |
1211
97.8 IPS |
|
Face Detection (SP)
|
100% |
2008
23.9 IPS |
|
Face Detection (HP)
|
100% |
1921
22.8 IPS |
|
Face Detection (Q)
|
95% |
3055
36.5 IPS |
|
Depth Estimation (SP)
|
99% |
1895
14.6 IPS |
|
Depth Estimation (HP)
|
99% |
1965
15.2 IPS |
|
Depth Estimation (Q)
|
64% |
3679
33.7 IPS |
|
Style Transfer (SP)
|
89% |
4776
6.20 IPS |
|
Style Transfer (HP)
|
89% |
4794
6.22 IPS |
|
Style Transfer (Q)
|
98% |
9198
11.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
1029
38.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
1011
37.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
2205
81.7 IPS |
|
Text Classification (SP)
|
100% |
252
335.8 IPS |
|
Text Classification (HP)
|
99% |
260
346.9 IPS |
|
Text Classification (Q)
|
88% |
339
457.4 IPS |
|
Machine Translation (SP)
|
100% |
659
11.3 IPS |
|
Machine Translation (HP)
|
100% |
643
11.1 IPS |
|
Machine Translation (Q)
|
50% |
310
11.0 IPS |