User | DoomSlayer |
Upload Date | November 09 2024 05:40 PM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | ARM Qualcomm |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi M2012K11AI |
Model ID | Xiaomi M2012K11AI |
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 @ 3.19 GHz |
Memory Information | |
---|---|
Size | 5.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
173
32.1 IPS |
|
Image Classification (HP)
|
100% |
174
32.3 IPS |
|
Image Classification (Q)
|
96% |
1307
244.1 IPS |
|
Image Segmentation (SP)
|
100% |
221
3.58 IPS |
|
Image Segmentation (HP)
|
100% |
223
3.62 IPS |
|
Image Segmentation (Q)
|
98% |
1233
20.1 IPS |
|
Pose Estimation (SP)
|
100% |
290
0.34 IPS |
|
Pose Estimation (HP)
|
100% |
290
0.34 IPS |
|
Pose Estimation (Q)
|
96% |
13265
15.5 IPS |
|
Object Detection (SP)
|
100% |
169
13.4 IPS |
|
Object Detection (HP)
|
100% |
171
13.5 IPS |
|
Object Detection (Q)
|
84% |
1264
102.0 IPS |
|
Face Detection (SP)
|
100% |
401
4.76 IPS |
|
Face Detection (HP)
|
100% |
407
4.83 IPS |
|
Face Detection (Q)
|
97% |
2150
25.6 IPS |
|
Depth Estimation (SP)
|
100% |
337
2.59 IPS |
|
Depth Estimation (HP)
|
99% |
338
2.60 IPS |
|
Depth Estimation (Q)
|
0% |
0
50.6 IPS |
|
Style Transfer (SP)
|
100% |
546
0.70 IPS |
|
Style Transfer (HP)
|
100% |
549
0.71 IPS |
|
Style Transfer (Q)
|
98% |
18717
24.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
167
6.16 IPS |
|
Image Super-Resolution (HP)
|
100% |
167
6.17 IPS |
|
Image Super-Resolution (Q)
|
97% |
666
24.7 IPS |
|
Text Classification (SP)
|
100% |
257
343.0 IPS |
|
Text Classification (HP)
|
100% |
258
343.8 IPS |
|
Text Classification (Q)
|
93% |
315
422.4 IPS |
|
Machine Translation (SP)
|
100% |
399
6.87 IPS |
|
Machine Translation (HP)
|
100% |
401
6.91 IPS |
|
Machine Translation (Q)
|
0% |
0
2.07 IPS |