User | rennsport |
Upload Date | December 20 2024 06:57 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 23021RAAEG |
Model ID | Xiaomi 23021RAAEG |
Motherboard | bengal |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3337 revision 0 |
Base Frequency | 1.90 GHz |
Cluster 1 | 4 Cores @ 1.90 GHz |
Cluster 2 | 4 Cores @ 2.80 GHz |
Memory Information | |
---|---|
Size | 3.56 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
56
10.3 IPS |
|
Image Classification (HP)
|
100% |
56
10.5 IPS |
|
Image Classification (Q)
|
96% |
472
88.1 IPS |
|
Image Segmentation (SP)
|
100% |
76
1.22 IPS |
|
Image Segmentation (HP)
|
100% |
76
1.23 IPS |
|
Image Segmentation (Q)
|
98% |
646
10.5 IPS |
|
Pose Estimation (SP)
|
100% |
107
0.13 IPS |
|
Pose Estimation (HP)
|
100% |
105
0.12 IPS |
|
Pose Estimation (Q)
|
98% |
207
0.24 IPS |
|
Object Detection (SP)
|
100% |
56
4.46 IPS |
|
Object Detection (HP)
|
100% |
57
4.50 IPS |
|
Object Detection (Q)
|
85% |
522
42.0 IPS |
|
Face Detection (SP)
|
100% |
145
1.72 IPS |
|
Face Detection (HP)
|
100% |
146
1.73 IPS |
|
Face Detection (Q)
|
97% |
1097
13.1 IPS |
|
Depth Estimation (SP)
|
100% |
129
0.99 IPS |
|
Depth Estimation (HP)
|
99% |
129
1.00 IPS |
|
Depth Estimation (Q)
|
64% |
2091
18.9 IPS |
|
Style Transfer (SP)
|
100% |
122
0.16 IPS |
|
Style Transfer (HP)
|
100% |
165
0.21 IPS |
|
Style Transfer (Q)
|
98% |
5662
7.30 IPS |
|
Image Super-Resolution (SP)
|
100% |
56
2.07 IPS |
|
Image Super-Resolution (HP)
|
100% |
56
2.08 IPS |
|
Image Super-Resolution (Q)
|
97% |
111
4.12 IPS |
|
Text Classification (SP)
|
100% |
79
105.7 IPS |
|
Text Classification (HP)
|
100% |
80
106.3 IPS |
|
Text Classification (Q)
|
93% |
147
196.7 IPS |
|
Machine Translation (SP)
|
100% |
135
2.33 IPS |
|
Machine Translation (HP)
|
100% |
135
2.32 IPS |
|
Machine Translation (Q)
|
0% |
0
1.06 IPS |