User | LinFengJun |
Upload Date | October 22 2024 07:27 AM |
Views | 3 |
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% |
89
16.6 IPS |
|
Image Classification (HP)
|
100% |
81
15.1 IPS |
|
Image Classification (Q)
|
100% |
192
35.7 IPS |
|
Image Segmentation (SP)
|
100% |
99
1.61 IPS |
|
Image Segmentation (HP)
|
100% |
107
1.74 IPS |
|
Image Segmentation (Q)
|
98% |
213
3.46 IPS |
|
Pose Estimation (SP)
|
100% |
338
0.39 IPS |
|
Pose Estimation (HP)
|
100% |
334
0.39 IPS |
|
Pose Estimation (Q)
|
84% |
389
0.46 IPS |
|
Object Detection (SP)
|
100% |
72
5.75 IPS |
|
Object Detection (HP)
|
100% |
72
5.72 IPS |
|
Object Detection (Q)
|
83% |
175
14.1 IPS |
|
Face Detection (SP)
|
100% |
195
2.32 IPS |
|
Face Detection (HP)
|
100% |
189
2.24 IPS |
|
Face Detection (Q)
|
95% |
444
5.30 IPS |
|
Depth Estimation (SP)
|
100% |
265
2.04 IPS |
|
Depth Estimation (HP)
|
99% |
253
1.95 IPS |
|
Depth Estimation (Q)
|
64% |
410
3.75 IPS |
|
Style Transfer (SP)
|
89% |
727
0.94 IPS |
|
Style Transfer (HP)
|
89% |
597
0.77 IPS |
|
Style Transfer (Q)
|
98% |
996
1.28 IPS |
|
Image Super-Resolution (SP)
|
100% |
154
5.69 IPS |
|
Image Super-Resolution (HP)
|
100% |
178
6.57 IPS |
|
Image Super-Resolution (Q)
|
97% |
229
8.50 IPS |
|
Text Classification (SP)
|
100% |
94
125.8 IPS |
|
Text Classification (HP)
|
100% |
86
115.1 IPS |
|
Text Classification (Q)
|
88% |
147
197.7 IPS |
|
Machine Translation (SP)
|
100% |
163
2.81 IPS |
|
Machine Translation (HP)
|
100% |
164
2.83 IPS |
|
Machine Translation (Q)
|
50% |
138
4.90 IPS |