User | Vaitek |
Upload Date | August 18 2024 08:19 AM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | ARM Qualcomm |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 23043RP34G |
Model ID | Xiaomi 23043RP34G |
Motherboard | pipa |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 3.19 GHz |
Memory Information | |
---|---|
Size | 7.43 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
33
6.08 IPS |
|
Image Classification (HP)
|
100% |
33
6.13 IPS |
|
Image Classification (Q)
|
97% |
96
17.9 IPS |
|
Image Segmentation (SP)
|
100% |
42
0.68 IPS |
|
Image Segmentation (HP)
|
100% |
42
0.68 IPS |
|
Image Segmentation (Q)
|
98% |
83
1.35 IPS |
|
Pose Estimation (SP)
|
100% |
64
0.07 IPS |
|
Pose Estimation (HP)
|
100% |
64
0.07 IPS |
|
Pose Estimation (Q)
|
98% |
251
0.29 IPS |
|
Object Detection (SP)
|
100% |
33
2.65 IPS |
|
Object Detection (HP)
|
100% |
34
2.68 IPS |
|
Object Detection (Q)
|
89% |
103
8.28 IPS |
|
Face Detection (SP)
|
100% |
78
0.92 IPS |
|
Face Detection (HP)
|
100% |
78
0.93 IPS |
|
Face Detection (Q)
|
97% |
204
2.43 IPS |
|
Depth Estimation (SP)
|
100% |
76
0.59 IPS |
|
Depth Estimation (HP)
|
100% |
77
0.59 IPS |
|
Depth Estimation (Q)
|
73% |
197
1.61 IPS |
|
Style Transfer (SP)
|
100% |
135
0.17 IPS |
|
Style Transfer (HP)
|
100% |
135
0.17 IPS |
|
Style Transfer (Q)
|
98% |
358
0.46 IPS |
|
Image Super-Resolution (SP)
|
100% |
40
1.48 IPS |
|
Image Super-Resolution (HP)
|
100% |
40
1.49 IPS |
|
Image Super-Resolution (Q)
|
97% |
152
5.62 IPS |
|
Text Classification (SP)
|
100% |
56
74.9 IPS |
|
Text Classification (HP)
|
100% |
57
75.8 IPS |
|
Text Classification (Q)
|
91% |
96
129.2 IPS |
|
Machine Translation (SP)
|
100% |
84
1.45 IPS |
|
Machine Translation (HP)
|
100% |
85
1.46 IPS |
|
Machine Translation (Q)
|
57% |
75
1.83 IPS |