Upload Date | August 08 2025 05:11 PM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm SM8750 |
System Information | |
---|---|
Operating System | Android 15 |
Model | HONOR MBH-N49 |
Model ID | HONOR MBH-N49 |
Motherboard | MBH |
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 | 14.89 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1307
243.0 IPS |
|
Image Classification (HP)
|
100% |
828
154.0 IPS |
|
Image Classification (Q)
|
100% |
1884
350.4 IPS |
|
Image Segmentation (SP)
|
100% |
1068
17.3 IPS |
|
Image Segmentation (HP)
|
100% |
1043
16.9 IPS |
|
Image Segmentation (Q)
|
98% |
2330
37.9 IPS |
|
Pose Estimation (SP)
|
100% |
2455
2.86 IPS |
|
Pose Estimation (HP)
|
100% |
2377
2.77 IPS |
|
Pose Estimation (Q)
|
84% |
5001
5.93 IPS |
|
Object Detection (SP)
|
98% |
682
54.2 IPS |
|
Object Detection (HP)
|
98% |
726
57.8 IPS |
|
Object Detection (Q)
|
83% |
1074
86.7 IPS |
|
Face Detection (SP)
|
100% |
2079
24.7 IPS |
|
Face Detection (HP)
|
100% |
2153
25.6 IPS |
|
Face Detection (Q)
|
95% |
2974
35.5 IPS |
|
Depth Estimation (SP)
|
99% |
1938
15.0 IPS |
|
Depth Estimation (HP)
|
99% |
1953
15.1 IPS |
|
Depth Estimation (Q)
|
64% |
3544
32.5 IPS |
|
Style Transfer (SP)
|
89% |
5006
6.50 IPS |
|
Style Transfer (HP)
|
89% |
4919
6.39 IPS |
|
Style Transfer (Q)
|
98% |
10809
13.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
936
34.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
979
36.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
2271
84.2 IPS |
|
Text Classification (SP)
|
100% |
265
353.4 IPS |
|
Text Classification (HP)
|
99% |
260
347.4 IPS |
|
Text Classification (Q)
|
88% |
290
390.9 IPS |
|
Machine Translation (SP)
|
100% |
419
7.22 IPS |
|
Machine Translation (HP)
|
100% |
440
7.57 IPS |
|
Machine Translation (Q)
|
50% |
192
6.82 IPS |