Upload Date | August 16 2024 04:11 PM |
Views | 8 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | ARM Qualcomm |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi Redmi K30 Pro Zoom Edition |
Model ID | Xiaomi Redmi K30 Pro Zoom Edition |
Motherboard | kona |
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% |
96
17.9 IPS |
|
Image Classification (HP)
|
100% |
98
18.2 IPS |
|
Image Classification (Q)
|
97% |
237
44.3 IPS |
|
Image Segmentation (SP)
|
100% |
127
2.06 IPS |
|
Image Segmentation (HP)
|
100% |
129
2.08 IPS |
|
Image Segmentation (Q)
|
98% |
253
4.12 IPS |
|
Pose Estimation (SP)
|
100% |
168
0.20 IPS |
|
Pose Estimation (HP)
|
100% |
168
0.20 IPS |
|
Pose Estimation (Q)
|
98% |
626
0.73 IPS |
|
Object Detection (SP)
|
100% |
96
7.60 IPS |
|
Object Detection (HP)
|
100% |
96
7.64 IPS |
|
Object Detection (Q)
|
89% |
260
20.8 IPS |
|
Face Detection (SP)
|
100% |
246
2.92 IPS |
|
Face Detection (HP)
|
100% |
251
2.98 IPS |
|
Face Detection (Q)
|
97% |
526
6.28 IPS |
|
Depth Estimation (SP)
|
100% |
210
1.62 IPS |
|
Depth Estimation (HP)
|
100% |
76
0.59 IPS |
|
Depth Estimation (Q)
|
73% |
189
1.54 IPS |
|
Style Transfer (SP)
|
100% |
134
0.17 IPS |
|
Style Transfer (HP)
|
100% |
371
0.48 IPS |
|
Style Transfer (Q)
|
98% |
1074
1.38 IPS |
|
Image Super-Resolution (SP)
|
100% |
109
4.02 IPS |
|
Image Super-Resolution (HP)
|
100% |
109
4.01 IPS |
|
Image Super-Resolution (Q)
|
97% |
389
14.4 IPS |
|
Text Classification (SP)
|
100% |
145
193.4 IPS |
|
Text Classification (HP)
|
100% |
146
194.5 IPS |
|
Text Classification (Q)
|
91% |
252
339.1 IPS |
|
Machine Translation (SP)
|
100% |
252
4.34 IPS |
|
Machine Translation (HP)
|
100% |
253
4.35 IPS |
|
Machine Translation (Q)
|
57% |
180
4.40 IPS |