User | Petenka315 |
Upload Date | May 05 2025 03:18 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
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 | 14.76 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
155
28.8 IPS |
|
Image Classification (HP)
|
100% |
15142
2.82 KIPS |
|
Image Classification (Q)
|
97% |
39305
7.34 KIPS |
|
Image Segmentation (SP)
|
100% |
204
3.31 IPS |
|
Image Segmentation (HP)
|
100% |
10518
170.5 IPS |
|
Image Segmentation (Q)
|
98% |
31747
516.2 IPS |
|
Pose Estimation (SP)
|
100% |
282
0.33 IPS |
|
Pose Estimation (HP)
|
100% |
83583
97.5 IPS |
|
Pose Estimation (Q)
|
98% |
328661
384.7 IPS |
|
Object Detection (SP)
|
100% |
213
16.9 IPS |
|
Object Detection (HP)
|
100% |
13865
1.10 KIPS |
|
Object Detection (Q)
|
85% |
17102
1.38 KIPS |
|
Face Detection (SP)
|
100% |
431
5.12 IPS |
|
Face Detection (HP)
|
100% |
29377
349.1 IPS |
|
Face Detection (Q)
|
97% |
108975
1.30 KIPS |
|
Depth Estimation (SP)
|
100% |
363
2.80 IPS |
|
Depth Estimation (HP)
|
99% |
62952
485.0 IPS |
|
Depth Estimation (Q)
|
63% |
115825
1.07 KIPS |
|
Style Transfer (SP)
|
100% |
684
0.88 IPS |
|
Style Transfer (HP)
|
98% |
73181
94.4 IPS |
|
Style Transfer (Q)
|
98% |
368804
475.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
180
6.65 IPS |
|
Image Super-Resolution (HP)
|
100% |
40300
1.49 KIPS |
|
Image Super-Resolution (Q)
|
97% |
101395
3.76 KIPS |
|
Text Classification (SP)
|
100% |
317
422.5 IPS |
|
Text Classification (HP)
|
100% |
3087
4.12 KIPS |
|
Text Classification (Q)
|
93% |
6664
8.94 KIPS |
|
Machine Translation (SP)
|
100% |
553
9.53 IPS |
|
Machine Translation (HP)
|
100% |
3621
62.4 IPS |
|
Machine Translation (Q)
|
56% |
2346
60.4 IPS |