Upload Date | August 18 2025 05:20 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Xiaomi 25019PNF3C |
Model ID | Xiaomi 25019PNF3C |
Motherboard | sun |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm ARMv8 |
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 | 14.76 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
416
77.3 IPS |
|
Image Classification (HP)
|
100% |
406
75.5 IPS |
|
Image Classification (Q)
|
99% |
1113
207.5 IPS |
|
Image Segmentation (SP)
|
100% |
501
8.13 IPS |
|
Image Segmentation (HP)
|
100% |
512
8.30 IPS |
|
Image Segmentation (Q)
|
98% |
1035
16.8 IPS |
|
Pose Estimation (SP)
|
100% |
679
0.79 IPS |
|
Pose Estimation (HP)
|
100% |
667
0.78 IPS |
|
Pose Estimation (Q)
|
98% |
1988
2.33 IPS |
|
Object Detection (SP)
|
100% |
281
22.3 IPS |
|
Object Detection (HP)
|
100% |
363
28.8 IPS |
|
Object Detection (Q)
|
87% |
1208
96.9 IPS |
|
Face Detection (SP)
|
100% |
968
11.5 IPS |
|
Face Detection (HP)
|
100% |
964
11.5 IPS |
|
Face Detection (Q)
|
97% |
2336
27.9 IPS |
|
Depth Estimation (SP)
|
100% |
828
6.38 IPS |
|
Depth Estimation (HP)
|
99% |
830
6.40 IPS |
|
Depth Estimation (Q)
|
64% |
2066
18.7 IPS |
|
Style Transfer (SP)
|
100% |
1309
1.68 IPS |
|
Style Transfer (HP)
|
100% |
1171
1.51 IPS |
|
Style Transfer (Q)
|
98% |
3045
3.93 IPS |
|
Image Super-Resolution (SP)
|
100% |
460
17.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
466
17.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
1700
63.0 IPS |
|
Text Classification (SP)
|
100% |
648
864.5 IPS |
|
Text Classification (HP)
|
100% |
639
853.2 IPS |
|
Text Classification (Q)
|
91% |
1064
1.43 KIPS |
|
Machine Translation (SP)
|
100% |
993
17.1 IPS |
|
Machine Translation (HP)
|
100% |
980
16.9 IPS |
|
Machine Translation (Q)
|
57% |
752
18.4 IPS |