Upload Date | May 07 2024 11:04 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi 21061119BI |
Model ID | Xiaomi 21061119BI |
Motherboard | selene |
CPU Information | |
---|---|
Name | ARM MT6769H |
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 | 5.58 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
73
13.7 IPS |
|
Image Classification (F16)
|
100% |
120
22.5 IPS |
|
Image Classification (I8)
|
97% |
115
21.6 IPS |
|
Image Segmentation (F32)
|
100% |
107
1.79 IPS |
|
Image Segmentation (F16)
|
100% |
183
3.05 IPS |
|
Image Segmentation (I8)
|
98% |
173
2.90 IPS |
|
Pose Estimation (F32)
|
100% |
57
0.07 IPS |
|
Pose Estimation (F16)
|
100% |
79
0.10 IPS |
|
Pose Estimation (I8)
|
100% |
79
0.10 IPS |
|
Object Detection (F32)
|
100% |
59
4.37 IPS |
|
Object Detection (F16)
|
100% |
94
7.01 IPS |
|
Object Detection (I8)
|
62% |
87
6.48 IPS |
|
Face Detection (F32)
|
100% |
237
2.82 IPS |
|
Face Detection (F16)
|
98% |
363
4.32 IPS |
|
Face Detection (I8)
|
86% |
340
4.04 IPS |
|
Depth Estimation (F32)
|
100% |
126
0.98 IPS |
|
Depth Estimation (F16)
|
100% |
175
1.36 IPS |
|
Depth Estimation (I8)
|
95% |
174
1.35 IPS |
|
Style Transfer (F32)
|
100% |
244
0.32 IPS |
|
Style Transfer (F16)
|
100% |
367
0.48 IPS |
|
Style Transfer (I8)
|
98% |
366
0.48 IPS |
|
Image Super-Resolution (F32)
|
100% |
71
2.54 IPS |
|
Image Super-Resolution (F16)
|
100% |
108
3.87 IPS |
|
Image Super-Resolution (I8)
|
98% |
107
3.83 IPS |
|
Text Classification (F32)
|
100% |
59
84.9 IPS |
|
Text Classification (F16)
|
100% |
59
84.8 IPS |
|
Text Classification (I8)
|
92% |
83
119.1 IPS |
|
Machine Translation (F32)
|
100% |
113
2.09 IPS |
|
Machine Translation (F16)
|
100% |
113
2.09 IPS |
|
Machine Translation (I8)
|
64% |
117
2.16 IPS |