Upload Date | December 29 2024 01:04 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT6769Z |
System Information | |
---|---|
Operating System | Android 12 |
Model | Xiaomi M2003J15SC |
Model ID | Xiaomi M2003J15SC |
Motherboard | merlinnfc |
CPU Information | |
---|---|
Name | ARM MT6769Z |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 2.63 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
90
16.7 IPS |
|
Image Classification (HP)
|
100% |
93
17.3 IPS |
|
Image Classification (Q)
|
100% |
207
38.5 IPS |
|
Image Segmentation (SP)
|
100% |
118
1.92 IPS |
|
Image Segmentation (HP)
|
100% |
115
1.86 IPS |
|
Image Segmentation (Q)
|
98% |
259
4.20 IPS |
|
Pose Estimation (SP)
|
100% |
440
0.51 IPS |
|
Pose Estimation (HP)
|
100% |
440
0.51 IPS |
|
Pose Estimation (Q)
|
84% |
405
0.48 IPS |
|
Object Detection (SP)
|
100% |
84
6.63 IPS |
|
Object Detection (HP)
|
100% |
88
6.94 IPS |
|
Object Detection (Q)
|
83% |
196
15.8 IPS |
|
Face Detection (SP)
|
100% |
293
3.48 IPS |
|
Face Detection (HP)
|
100% |
298
3.54 IPS |
|
Face Detection (Q)
|
95% |
554
6.62 IPS |
|
Depth Estimation (SP)
|
100% |
381
2.94 IPS |
|
Depth Estimation (HP)
|
99% |
344
2.65 IPS |
|
Depth Estimation (Q)
|
64% |
456
4.18 IPS |
|
Style Transfer (SP)
|
89% |
790
1.03 IPS |
|
Style Transfer (HP)
|
89% |
747
0.97 IPS |
|
Style Transfer (Q)
|
98% |
1050
1.35 IPS |
|
Image Super-Resolution (SP)
|
100% |
195
7.20 IPS |
|
Image Super-Resolution (HP)
|
100% |
198
7.31 IPS |
|
Image Super-Resolution (Q)
|
97% |
238
8.80 IPS |
|
Text Classification (SP)
|
100% |
121
161.3 IPS |
|
Text Classification (HP)
|
100% |
121
161.6 IPS |
|
Text Classification (Q)
|
88% |
164
221.0 IPS |
|
Machine Translation (SP)
|
100% |
214
3.69 IPS |
|
Machine Translation (HP)
|
100% |
216
3.72 IPS |
|
Machine Translation (Q)
|
50% |
149
5.29 IPS |