User | andreadandrea |
Upload Date | January 04 2025 04:34 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | Qualcomm Snapdragon 780G |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi Mi 11 Lite |
Model ID | Xiaomi M2101K9G |
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 | 7.16 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
30
5.57 IPS |
|
Image Classification (HP)
|
100% |
31
5.78 IPS |
|
Image Classification (Q)
|
99% |
6315
1.18 KIPS |
|
Image Segmentation (SP)
|
100% |
40
0.65 IPS |
|
Image Segmentation (HP)
|
100% |
41
0.66 IPS |
|
Image Segmentation (Q)
|
98% |
4191
68.2 IPS |
|
Pose Estimation (SP)
|
100% |
48
0.06 IPS |
|
Pose Estimation (HP)
|
100% |
48
0.06 IPS |
|
Pose Estimation (Q)
|
94% |
30349
35.6 IPS |
|
Object Detection (SP)
|
100% |
31
2.47 IPS |
|
Object Detection (HP)
|
100% |
31
2.47 IPS |
|
Object Detection (Q)
|
88% |
3311
265.2 IPS |
|
Face Detection (SP)
|
100% |
74
0.88 IPS |
|
Face Detection (HP)
|
100% |
76
0.90 IPS |
|
Face Detection (Q)
|
97% |
11380
135.7 IPS |
|
Depth Estimation (SP)
|
100% |
67
0.52 IPS |
|
Depth Estimation (HP)
|
99% |
68
0.52 IPS |
|
Depth Estimation (Q)
|
64% |
16900
155.6 IPS |
|
Style Transfer (SP)
|
100% |
129
0.17 IPS |
|
Style Transfer (HP)
|
100% |
131
0.17 IPS |
|
Style Transfer (Q)
|
98% |
63060
81.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
40
1.46 IPS |
|
Image Super-Resolution (HP)
|
100% |
39
1.44 IPS |
|
Image Super-Resolution (Q)
|
97% |
13404
496.7 IPS |
|
Text Classification (SP)
|
100% |
52
69.5 IPS |
|
Text Classification (HP)
|
100% |
52
69.9 IPS |
|
Text Classification (Q)
|
94% |
1814
2.43 KIPS |
|
Machine Translation (SP)
|
100% |
84
1.45 IPS |
|
Machine Translation (HP)
|
100% |
85
1.46 IPS |
|
Machine Translation (Q)
|
50% |
268
9.29 IPS |