Upload Date | May 31 2025 08:16 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Qualcomm |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi 2209116AG |
Model ID | Xiaomi 2209116AG |
Motherboard | sweet |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 13 part 2052 revision 14 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.30 GHz |
Memory Information | |
---|---|
Size | 7.39 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
201
37.3 IPS |
|
Image Classification (HP)
|
100% |
168
31.2 IPS |
|
Image Classification (Q)
|
100% |
455
84.6 IPS |
|
Image Segmentation (SP)
|
100% |
218
3.53 IPS |
|
Image Segmentation (HP)
|
100% |
218
3.54 IPS |
|
Image Segmentation (Q)
|
98% |
512
8.33 IPS |
|
Pose Estimation (SP)
|
100% |
874
1.02 IPS |
|
Pose Estimation (HP)
|
100% |
852
0.99 IPS |
|
Pose Estimation (Q)
|
84% |
1133
1.34 IPS |
|
Object Detection (SP)
|
100% |
171
13.6 IPS |
|
Object Detection (HP)
|
100% |
171
13.5 IPS |
|
Object Detection (Q)
|
83% |
455
36.8 IPS |
|
Face Detection (SP)
|
100% |
588
6.98 IPS |
|
Face Detection (HP)
|
100% |
575
6.84 IPS |
|
Face Detection (Q)
|
95% |
1071
12.8 IPS |
|
Depth Estimation (SP)
|
100% |
716
5.52 IPS |
|
Depth Estimation (HP)
|
99% |
768
5.92 IPS |
|
Depth Estimation (Q)
|
64% |
1052
9.63 IPS |
|
Style Transfer (SP)
|
89% |
1383
1.80 IPS |
|
Style Transfer (HP)
|
89% |
1383
1.80 IPS |
|
Style Transfer (Q)
|
98% |
2605
3.36 IPS |
|
Image Super-Resolution (SP)
|
100% |
410
15.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
413
15.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
640
23.7 IPS |
|
Text Classification (SP)
|
100% |
192
256.7 IPS |
|
Text Classification (HP)
|
100% |
193
257.2 IPS |
|
Text Classification (Q)
|
88% |
374
503.8 IPS |
|
Machine Translation (SP)
|
100% |
349
6.02 IPS |
|
Machine Translation (HP)
|
100% |
348
5.99 IPS |
|
Machine Translation (Q)
|
50% |
269
9.54 IPS |