Upload Date | August 30 2024 10:56 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 2106118C |
Model ID | Xiaomi 2106118C |
Motherboard | odin |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Odin |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 3.00 GHz |
Memory Information | |
---|---|
Size | 7.05 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
465
86.9 IPS |
|
Image Classification (F16)
|
100% |
1040
194.6 IPS |
|
Image Classification (I8)
|
94% |
17
3.22 IPS |
|
Image Segmentation (F32)
|
100% |
666
11.1 IPS |
|
Image Segmentation (F16)
|
100% |
920
15.4 IPS |
|
Image Segmentation (I8)
|
98% |
470
7.86 IPS |
|
Pose Estimation (F32)
|
100% |
1417
1.72 IPS |
|
Pose Estimation (F16)
|
100% |
5172
6.26 IPS |
|
Pose Estimation (I8)
|
100% |
1335
1.62 IPS |
|
Object Detection (F32)
|
100% |
350
26.1 IPS |
|
Object Detection (F16)
|
100% |
536
40.0 IPS |
|
Object Detection (I8)
|
0% |
1647
123.0 IPS |
|
Face Detection (F32)
|
100% |
1245
14.8 IPS |
|
Face Detection (F16)
|
97% |
1888
22.5 IPS |
|
Face Detection (I8)
|
86% |
994
11.8 IPS |
|
Depth Estimation (F32)
|
100% |
460
3.57 IPS |
|
Depth Estimation (F16)
|
100% |
613
4.75 IPS |
|
Depth Estimation (I8)
|
74% |
6923
53.7 IPS |
|
Style Transfer (F32)
|
100% |
1673
2.20 IPS |
|
Style Transfer (F16)
|
100% |
2186
2.87 IPS |
|
Style Transfer (I8)
|
19% |
572
0.75 IPS |
|
Image Super-Resolution (F32)
|
100% |
764
27.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
2281
81.5 IPS |
|
Image Super-Resolution (I8)
|
98% |
266
9.51 IPS |
|
Text Classification (F32)
|
100% |
1
1.76 IPS |
|
Text Classification (F16)
|
100% |
38
55.1 IPS |
|
Text Classification (I8)
|
94% |
26
37.3 IPS |
|
Machine Translation (F32)
|
100% |
119
2.20 IPS |
|
Machine Translation (F16)
|
100% |
408
7.50 IPS |
|
Machine Translation (I8)
|
64% |
452
8.33 IPS |