Upload Date | January 07 2025 03:27 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM Qualcomm |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi Mi 10 |
Model ID | Xiaomi Mi 10 |
Motherboard | umi |
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 @ 2.84 GHz |
Memory Information | |
---|---|
Size | 7.43 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
389
72.4 IPS |
|
Image Classification (HP)
|
100% |
621
115.5 IPS |
|
Image Classification (Q)
|
97% |
1218
227.2 IPS |
|
Image Segmentation (SP)
|
100% |
405
6.56 IPS |
|
Image Segmentation (HP)
|
100% |
41
0.66 IPS |
|
Image Segmentation (Q)
|
98% |
1162
18.9 IPS |
|
Pose Estimation (SP)
|
100% |
1414
1.65 IPS |
|
Pose Estimation (HP)
|
100% |
5308
6.19 IPS |
|
Pose Estimation (Q)
|
96% |
11268
13.2 IPS |
|
Object Detection (SP)
|
100% |
342
27.2 IPS |
|
Object Detection (HP)
|
100% |
32
2.53 IPS |
|
Object Detection (Q)
|
85% |
1298
104.5 IPS |
|
Face Detection (SP)
|
100% |
1067
12.7 IPS |
|
Face Detection (HP)
|
100% |
76
0.91 IPS |
|
Face Detection (Q)
|
97% |
2982
35.6 IPS |
|
Depth Estimation (SP)
|
99% |
176
1.36 IPS |
|
Depth Estimation (HP)
|
99% |
75
0.58 IPS |
|
Depth Estimation (Q)
|
22% |
235
53.8 IPS |
|
Style Transfer (SP)
|
100% |
228
0.29 IPS |
|
Style Transfer (HP)
|
100% |
134
0.17 IPS |
|
Style Transfer (Q)
|
98% |
976
1.26 IPS |
|
Image Super-Resolution (SP)
|
100% |
722
26.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
1939
71.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
4769
176.7 IPS |
|
Text Classification (SP)
|
71% |
9
13.2 IPS |
|
Text Classification (HP)
|
100% |
56
74.9 IPS |
|
Text Classification (Q)
|
93% |
76
102.0 IPS |
|
Machine Translation (SP)
|
100% |
87
1.51 IPS |
|
Machine Translation (HP)
|
100% |
86
1.49 IPS |
|
Machine Translation (Q)
|
54% |
66
1.87 IPS |