Upload Date | February 03 2025 09:50 AM |
Views | 41 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Xiaomi 25010PN30G |
Model ID | Xiaomi 25010PN30G |
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 | 14.74 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
402
74.7 IPS |
|
Image Classification (HP)
|
100% |
412
76.6 IPS |
|
Image Classification (Q)
|
99% |
1129
210.6 IPS |
|
Image Segmentation (SP)
|
100% |
530
8.59 IPS |
|
Image Segmentation (HP)
|
100% |
534
8.65 IPS |
|
Image Segmentation (Q)
|
98% |
1088
17.7 IPS |
|
Pose Estimation (SP)
|
100% |
693
0.81 IPS |
|
Pose Estimation (HP)
|
100% |
687
0.80 IPS |
|
Pose Estimation (Q)
|
98% |
2727
3.19 IPS |
|
Object Detection (SP)
|
100% |
385
30.6 IPS |
|
Object Detection (HP)
|
100% |
396
31.4 IPS |
|
Object Detection (Q)
|
87% |
1183
94.9 IPS |
|
Face Detection (SP)
|
100% |
977
11.6 IPS |
|
Face Detection (HP)
|
100% |
975
11.6 IPS |
|
Face Detection (Q)
|
97% |
2412
28.8 IPS |
|
Depth Estimation (SP)
|
100% |
855
6.58 IPS |
|
Depth Estimation (HP)
|
99% |
852
6.56 IPS |
|
Depth Estimation (Q)
|
64% |
1925
17.5 IPS |
|
Style Transfer (SP)
|
100% |
1458
1.87 IPS |
|
Style Transfer (HP)
|
100% |
1296
1.67 IPS |
|
Style Transfer (Q)
|
98% |
4198
5.41 IPS |
|
Image Super-Resolution (SP)
|
100% |
360
13.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
479
17.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
1432
53.1 IPS |
|
Text Classification (SP)
|
100% |
435
580.5 IPS |
|
Text Classification (HP)
|
100% |
435
580.9 IPS |
|
Text Classification (Q)
|
91% |
717
964.2 IPS |
|
Machine Translation (SP)
|
100% |
992
17.1 IPS |
|
Machine Translation (HP)
|
100% |
737
12.7 IPS |
|
Machine Translation (Q)
|
57% |
539
13.2 IPS |