Upload Date | April 16 2025 09:05 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
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% |
688
127.9 IPS |
|
Image Classification (HP)
|
100% |
856
159.2 IPS |
|
Image Classification (Q)
|
99% |
829
154.7 IPS |
|
Image Segmentation (SP)
|
100% |
1520
24.6 IPS |
|
Image Segmentation (HP)
|
100% |
2154
34.9 IPS |
|
Image Segmentation (Q)
|
98% |
2328
37.9 IPS |
|
Pose Estimation (SP)
|
100% |
1637
1.91 IPS |
|
Pose Estimation (HP)
|
100% |
2798
3.26 IPS |
|
Pose Estimation (Q)
|
96% |
2792
3.27 IPS |
|
Object Detection (SP)
|
100% |
541
42.9 IPS |
|
Object Detection (HP)
|
100% |
1197
95.0 IPS |
|
Object Detection (Q)
|
86% |
1075
86.4 IPS |
|
Face Detection (SP)
|
100% |
2964
35.2 IPS |
|
Face Detection (HP)
|
100% |
3399
40.4 IPS |
|
Face Detection (Q)
|
97% |
4391
52.4 IPS |
|
Depth Estimation (SP)
|
100% |
1614
12.4 IPS |
|
Depth Estimation (HP)
|
99% |
4620
35.7 IPS |
|
Depth Estimation (Q)
|
63% |
3818
35.5 IPS |
|
Style Transfer (SP)
|
100% |
5810
7.47 IPS |
|
Style Transfer (HP)
|
100% |
12443
16.0 IPS |
|
Style Transfer (Q)
|
98% |
12354
15.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
636
23.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
2146
79.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
2104
78.0 IPS |
|
Text Classification (SP)
|
100% |
202
269.4 IPS |
|
Text Classification (HP)
|
100% |
202
269.6 IPS |
|
Text Classification (Q)
|
91% |
335
450.4 IPS |
|
Machine Translation (SP)
|
100% |
437
7.54 IPS |
|
Machine Translation (HP)
|
100% |
651
11.2 IPS |
|
Machine Translation (Q)
|
57% |
282
6.89 IPS |