User | LinFengJun |
Upload Date | October 22 2024 12:02 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | MediaTek Helio G80 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Xiaomi Redmi 9 |
Model ID | Xiaomi M2004J19C |
Motherboard | lancelot |
CPU Information | |
---|---|
Name | ARM MT6769T |
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 | 3.61 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
97
18.1 IPS |
|
Image Classification (HP)
|
100% |
96
17.9 IPS |
|
Image Classification (Q)
|
100% |
208
38.8 IPS |
|
Image Segmentation (SP)
|
100% |
116
1.88 IPS |
|
Image Segmentation (HP)
|
100% |
115
1.87 IPS |
|
Image Segmentation (Q)
|
98% |
263
4.27 IPS |
|
Pose Estimation (SP)
|
100% |
469
0.55 IPS |
|
Pose Estimation (HP)
|
100% |
474
0.55 IPS |
|
Pose Estimation (Q)
|
84% |
413
0.49 IPS |
|
Object Detection (SP)
|
100% |
94
7.45 IPS |
|
Object Detection (HP)
|
100% |
92
7.30 IPS |
|
Object Detection (Q)
|
83% |
204
16.5 IPS |
|
Face Detection (SP)
|
100% |
298
3.54 IPS |
|
Face Detection (HP)
|
100% |
296
3.52 IPS |
|
Face Detection (Q)
|
95% |
568
6.78 IPS |
|
Depth Estimation (SP)
|
100% |
401
3.09 IPS |
|
Depth Estimation (HP)
|
99% |
369
2.84 IPS |
|
Depth Estimation (Q)
|
64% |
459
4.20 IPS |
|
Style Transfer (SP)
|
89% |
817
1.06 IPS |
|
Style Transfer (HP)
|
89% |
807
1.05 IPS |
|
Style Transfer (Q)
|
98% |
1111
1.43 IPS |
|
Image Super-Resolution (SP)
|
100% |
201
7.42 IPS |
|
Image Super-Resolution (HP)
|
100% |
201
7.41 IPS |
|
Image Super-Resolution (Q)
|
97% |
237
8.78 IPS |
|
Text Classification (SP)
|
100% |
117
156.5 IPS |
|
Text Classification (HP)
|
100% |
121
161.7 IPS |
|
Text Classification (Q)
|
88% |
200
269.7 IPS |
|
Machine Translation (SP)
|
100% |
229
3.94 IPS |
|
Machine Translation (HP)
|
100% |
224
3.86 IPS |
|
Machine Translation (Q)
|
50% |
151
5.38 IPS |