Upload Date | November 20 2024 04:55 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Xiaomi 24129PN74C |
Model ID | Xiaomi 24129PN74C |
Motherboard | sun |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 3 part 1 revision 4 |
Base Frequency | 3.53 GHz |
Cluster 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.32 GHz |
Memory Information | |
---|---|
Size | 10.86 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
999
186.9 IPS |
|
Image Classification (F16)
|
100% |
946
177.0 IPS |
|
Image Classification (I8)
|
97% |
1195
223.7 IPS |
|
Image Segmentation (F32)
|
100% |
1314
22.0 IPS |
|
Image Segmentation (F16)
|
100% |
1233
20.6 IPS |
|
Image Segmentation (I8)
|
98% |
1311
21.9 IPS |
|
Pose Estimation (F32)
|
100% |
1995
2.42 IPS |
|
Pose Estimation (F16)
|
100% |
1672
2.03 IPS |
|
Pose Estimation (I8)
|
100% |
6195
7.50 IPS |
|
Object Detection (F32)
|
100% |
837
62.5 IPS |
|
Object Detection (F16)
|
100% |
827
61.8 IPS |
|
Object Detection (I8)
|
61% |
1419
106.0 IPS |
|
Face Detection (F32)
|
100% |
2059
24.5 IPS |
|
Face Detection (F16)
|
100% |
2060
24.5 IPS |
|
Face Detection (I8)
|
86% |
2514
29.9 IPS |
|
Depth Estimation (F32)
|
100% |
1812
14.1 IPS |
|
Depth Estimation (F16)
|
100% |
1801
14.0 IPS |
|
Depth Estimation (I8)
|
95% |
2810
21.8 IPS |
|
Style Transfer (F32)
|
100% |
2900
3.82 IPS |
|
Style Transfer (F16)
|
100% |
2930
3.85 IPS |
|
Style Transfer (I8)
|
98% |
6741
8.87 IPS |
|
Image Super-Resolution (F32)
|
100% |
957
34.2 IPS |
|
Image Super-Resolution (F16)
|
100% |
941
33.6 IPS |
|
Image Super-Resolution (I8)
|
98% |
2494
89.1 IPS |
|
Text Classification (F32)
|
100% |
757
1.09 KIPS |
|
Text Classification (F16)
|
100% |
692
994.8 IPS |
|
Text Classification (I8)
|
92% |
481
691.7 IPS |
|
Machine Translation (F32)
|
100% |
1616
29.7 IPS |
|
Machine Translation (F16)
|
100% |
1634
30.1 IPS |
|
Machine Translation (I8)
|
64% |
640
11.8 IPS |