Upload Date | September 12 2025 08:53 PM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT6769H |
System Information | |
---|---|
Operating System | Android 12 |
Model | Xiaomi 21061119AG |
Model ID | Xiaomi 21061119AG |
Motherboard | selene |
CPU Information | |
---|---|
Name | ARM MT6769H |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 5.58 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
91
16.9 IPS |
|
Image Classification (HP)
|
100% |
93
17.3 IPS |
|
Image Classification (Q)
|
100% |
188
34.9 IPS |
|
Image Segmentation (SP)
|
100% |
116
1.88 IPS |
|
Image Segmentation (HP)
|
100% |
116
1.87 IPS |
|
Image Segmentation (Q)
|
98% |
233
3.78 IPS |
|
Pose Estimation (SP)
|
100% |
464
0.54 IPS |
|
Pose Estimation (HP)
|
100% |
468
0.55 IPS |
|
Pose Estimation (Q)
|
84% |
357
0.42 IPS |
|
Object Detection (SP)
|
100% |
92
7.26 IPS |
|
Object Detection (HP)
|
100% |
79
6.27 IPS |
|
Object Detection (Q)
|
83% |
173
14.0 IPS |
|
Face Detection (SP)
|
100% |
297
3.53 IPS |
|
Face Detection (HP)
|
100% |
270
3.21 IPS |
|
Face Detection (Q)
|
95% |
437
5.22 IPS |
|
Depth Estimation (SP)
|
100% |
349
2.69 IPS |
|
Depth Estimation (HP)
|
99% |
352
2.71 IPS |
|
Depth Estimation (Q)
|
64% |
357
3.27 IPS |
|
Style Transfer (SP)
|
89% |
722
0.94 IPS |
|
Style Transfer (HP)
|
89% |
679
0.88 IPS |
|
Style Transfer (Q)
|
98% |
777
1.00 IPS |
|
Image Super-Resolution (SP)
|
100% |
193
7.12 IPS |
|
Image Super-Resolution (HP)
|
100% |
194
7.15 IPS |
|
Image Super-Resolution (Q)
|
97% |
188
6.96 IPS |
|
Text Classification (SP)
|
100% |
94
125.2 IPS |
|
Text Classification (HP)
|
100% |
94
124.9 IPS |
|
Text Classification (Q)
|
88% |
149
200.6 IPS |
|
Machine Translation (SP)
|
100% |
182
3.14 IPS |
|
Machine Translation (HP)
|
100% |
182
3.13 IPS |
|
Machine Translation (Q)
|
50% |
119
4.22 IPS |