Upload Date | January 02 2025 05:33 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 24090RA29G |
Model ID | Xiaomi 24090RA29G |
Motherboard | malachite |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 4 Cores @ 2.50 GHz |
Memory Information | |
---|---|
Size | 7.25 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
81
15.1 IPS |
|
Image Classification (HP)
|
100% |
82
15.2 IPS |
|
Image Classification (Q)
|
99% |
266
49.7 IPS |
|
Image Segmentation (SP)
|
100% |
112
1.81 IPS |
|
Image Segmentation (HP)
|
100% |
113
1.82 IPS |
|
Image Segmentation (Q)
|
98% |
311
5.05 IPS |
|
Pose Estimation (SP)
|
100% |
139
0.16 IPS |
|
Pose Estimation (HP)
|
100% |
139
0.16 IPS |
|
Pose Estimation (Q)
|
98% |
573
0.67 IPS |
|
Object Detection (SP)
|
100% |
79
6.30 IPS |
|
Object Detection (HP)
|
100% |
80
6.33 IPS |
|
Object Detection (Q)
|
87% |
273
21.9 IPS |
|
Face Detection (SP)
|
100% |
229
2.72 IPS |
|
Face Detection (HP)
|
100% |
229
2.72 IPS |
|
Face Detection (Q)
|
97% |
614
7.32 IPS |
|
Depth Estimation (SP)
|
100% |
177
1.36 IPS |
|
Depth Estimation (HP)
|
99% |
178
1.37 IPS |
|
Depth Estimation (Q)
|
64% |
524
4.75 IPS |
|
Style Transfer (SP)
|
100% |
322
0.41 IPS |
|
Style Transfer (HP)
|
100% |
322
0.41 IPS |
|
Style Transfer (Q)
|
98% |
1074
1.39 IPS |
|
Image Super-Resolution (SP)
|
100% |
85
3.14 IPS |
|
Image Super-Resolution (HP)
|
100% |
85
3.14 IPS |
|
Image Super-Resolution (Q)
|
97% |
347
12.9 IPS |
|
Text Classification (SP)
|
100% |
116
154.3 IPS |
|
Text Classification (HP)
|
100% |
115
153.7 IPS |
|
Text Classification (Q)
|
91% |
289
388.0 IPS |
|
Machine Translation (SP)
|
100% |
194
3.34 IPS |
|
Machine Translation (HP)
|
100% |
193
3.32 IPS |
|
Machine Translation (Q)
|
57% |
248
6.05 IPS |