Upload Date | November 27 2024 06:52 AM |
Views | 2 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Xiaomi Redmi K50 Ultra |
Model ID | Xiaomi 22081212C |
Motherboard | diting |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
Base Frequency | 2.02 GHz |
Cluster 1 | 4 Cores @ 2.02 GHz |
Cluster 2 | 3 Cores @ 2.75 GHz |
Cluster 3 | 1 Core @ 3.19 GHz |
Memory Information | |
---|---|
Size | 10.91 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
453
84.7 IPS |
|
Image Classification (F16)
|
100% |
453
84.8 IPS |
|
Image Classification (I8)
|
97% |
776
145.3 IPS |
|
Image Segmentation (F32)
|
100% |
513
8.56 IPS |
|
Image Segmentation (F16)
|
100% |
529
8.84 IPS |
|
Image Segmentation (I8)
|
98% |
644
10.7 IPS |
|
Pose Estimation (F32)
|
100% |
982
1.19 IPS |
|
Pose Estimation (F16)
|
100% |
959
1.16 IPS |
|
Pose Estimation (I8)
|
100% |
3917
4.74 IPS |
|
Object Detection (F32)
|
100% |
380
28.4 IPS |
|
Object Detection (F16)
|
100% |
372
27.8 IPS |
|
Object Detection (I8)
|
61% |
903
67.4 IPS |
|
Face Detection (F32)
|
100% |
869
10.3 IPS |
|
Face Detection (F16)
|
100% |
867
10.3 IPS |
|
Face Detection (I8)
|
86% |
1345
16.0 IPS |
|
Depth Estimation (F32)
|
100% |
947
7.34 IPS |
|
Depth Estimation (F16)
|
100% |
949
7.36 IPS |
|
Depth Estimation (I8)
|
95% |
1979
15.3 IPS |
|
Style Transfer (F32)
|
100% |
1747
2.30 IPS |
|
Style Transfer (F16)
|
100% |
1749
2.30 IPS |
|
Style Transfer (I8)
|
98% |
4244
5.58 IPS |
|
Image Super-Resolution (F32)
|
100% |
576
20.6 IPS |
|
Image Super-Resolution (F16)
|
100% |
583
20.8 IPS |
|
Image Super-Resolution (I8)
|
98% |
1665
59.5 IPS |
|
Text Classification (F32)
|
100% |
461
662.8 IPS |
|
Text Classification (F16)
|
100% |
468
672.3 IPS |
|
Text Classification (I8)
|
92% |
363
521.7 IPS |
|
Machine Translation (F32)
|
100% |
904
16.6 IPS |
|
Machine Translation (F16)
|
100% |
933
17.2 IPS |
|
Machine Translation (I8)
|
64% |
371
6.84 IPS |