Upload Date | January 04 2025 09:31 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | ARM Renoir |
System Information | |
---|---|
Operating System | Android 12 |
Model | Xiaomi M2101K9C |
Model ID | Xiaomi M2101K9C |
Motherboard | renoir |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Renoir |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 0 |
Base Frequency | 1.90 GHz |
Cluster 1 | 4 Cores @ 1.90 GHz |
Cluster 2 | 3 Cores @ 2.21 GHz |
Cluster 3 | 1 Core @ 2.40 GHz |
Memory Information | |
---|---|
Size | 7.15 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
32
6.03 IPS |
|
Image Classification (HP)
|
100% |
33
6.14 IPS |
|
Image Classification (Q)
|
99% |
5213
972.3 IPS |
|
Image Segmentation (SP)
|
100% |
44
0.71 IPS |
|
Image Segmentation (HP)
|
100% |
44
0.71 IPS |
|
Image Segmentation (Q)
|
98% |
5461
88.8 IPS |
|
Pose Estimation (SP)
|
100% |
58
0.07 IPS |
|
Pose Estimation (HP)
|
100% |
58
0.07 IPS |
|
Pose Estimation (Q)
|
94% |
31380
36.8 IPS |
|
Object Detection (SP)
|
100% |
34
2.68 IPS |
|
Object Detection (HP)
|
100% |
34
2.67 IPS |
|
Object Detection (Q)
|
88% |
2917
233.7 IPS |
|
Face Detection (SP)
|
100% |
78
0.93 IPS |
|
Face Detection (HP)
|
100% |
79
0.94 IPS |
|
Face Detection (Q)
|
97% |
11719
139.7 IPS |
|
Depth Estimation (SP)
|
100% |
74
0.57 IPS |
|
Depth Estimation (HP)
|
99% |
75
0.58 IPS |
|
Depth Estimation (Q)
|
64% |
16148
148.7 IPS |
|
Style Transfer (SP)
|
100% |
144
0.18 IPS |
|
Style Transfer (HP)
|
100% |
143
0.18 IPS |
|
Style Transfer (Q)
|
98% |
61064
78.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
41
1.53 IPS |
|
Image Super-Resolution (HP)
|
100% |
41
1.51 IPS |
|
Image Super-Resolution (Q)
|
97% |
13417
497.2 IPS |
|
Text Classification (SP)
|
100% |
57
75.9 IPS |
|
Text Classification (HP)
|
100% |
56
74.5 IPS |
|
Text Classification (Q)
|
94% |
1628
2.18 KIPS |
|
Machine Translation (SP)
|
100% |
88
1.52 IPS |
|
Machine Translation (HP)
|
100% |
89
1.53 IPS |
|
Machine Translation (Q)
|
37% |
91
9.19 IPS |