User | LinFengJun |
Upload Date | October 20 2024 02:50 AM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
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% |
71
13.3 IPS |
|
Image Classification (HP)
|
100% |
114
21.1 IPS |
|
Image Classification (Q)
|
99% |
108
20.2 IPS |
|
Image Segmentation (SP)
|
100% |
103
1.68 IPS |
|
Image Segmentation (HP)
|
100% |
186
3.02 IPS |
|
Image Segmentation (Q)
|
98% |
172
2.80 IPS |
|
Pose Estimation (SP)
|
100% |
56
0.07 IPS |
|
Pose Estimation (HP)
|
100% |
77
0.09 IPS |
|
Pose Estimation (Q)
|
96% |
77
0.09 IPS |
|
Object Detection (SP)
|
100% |
58
4.59 IPS |
|
Object Detection (HP)
|
100% |
95
7.56 IPS |
|
Object Detection (Q)
|
83% |
93
7.49 IPS |
|
Face Detection (SP)
|
100% |
225
2.68 IPS |
|
Face Detection (HP)
|
100% |
344
4.09 IPS |
|
Face Detection (Q)
|
97% |
328
3.91 IPS |
|
Depth Estimation (SP)
|
100% |
120
0.93 IPS |
|
Depth Estimation (HP)
|
99% |
166
1.28 IPS |
|
Depth Estimation (Q)
|
62% |
134
1.27 IPS |
|
Style Transfer (SP)
|
100% |
235
0.30 IPS |
|
Style Transfer (HP)
|
100% |
356
0.46 IPS |
|
Style Transfer (Q)
|
98% |
354
0.46 IPS |
|
Image Super-Resolution (SP)
|
100% |
65
2.39 IPS |
|
Image Super-Resolution (HP)
|
100% |
100
3.68 IPS |
|
Image Super-Resolution (Q)
|
97% |
97
3.61 IPS |
|
Text Classification (SP)
|
100% |
69
91.9 IPS |
|
Text Classification (HP)
|
100% |
69
92.1 IPS |
|
Text Classification (Q)
|
91% |
103
138.0 IPS |
|
Machine Translation (SP)
|
100% |
122
2.09 IPS |
|
Machine Translation (HP)
|
100% |
121
2.09 IPS |
|
Machine Translation (Q)
|
57% |
96
2.35 IPS |