Upload Date | October 21 2024 04:49 PM |
Views | 3 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 2201122C |
Model ID | Xiaomi 2201122C |
Motherboard | taro |
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 | 1.78 GHz |
Cluster 1 | 4 Cores @ 1.79 GHz |
Cluster 2 | 3 Cores @ 2.50 GHz |
Cluster 3 | 1 Core @ 3.00 GHz |
Memory Information | |
---|---|
Size | 10.93 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
230
43.0 IPS |
|
Image Classification (F16)
|
100% |
233
43.6 IPS |
|
Image Classification (I8)
|
97% |
314
58.7 IPS |
|
Image Segmentation (F32)
|
100% |
320
5.34 IPS |
|
Image Segmentation (F16)
|
100% |
317
5.30 IPS |
|
Image Segmentation (I8)
|
98% |
381
6.37 IPS |
|
Pose Estimation (F32)
|
100% |
802
0.97 IPS |
|
Pose Estimation (F16)
|
100% |
774
0.94 IPS |
|
Pose Estimation (I8)
|
100% |
2712
3.28 IPS |
|
Object Detection (F32)
|
100% |
243
18.1 IPS |
|
Object Detection (F16)
|
100% |
235
17.6 IPS |
|
Object Detection (I8)
|
61% |
465
34.7 IPS |
|
Face Detection (F32)
|
100% |
561
6.67 IPS |
|
Face Detection (F16)
|
100% |
559
6.65 IPS |
|
Face Detection (I8)
|
86% |
921
11.0 IPS |
|
Depth Estimation (F32)
|
100% |
654
5.07 IPS |
|
Depth Estimation (F16)
|
100% |
670
5.20 IPS |
|
Depth Estimation (I8)
|
95% |
1104
8.56 IPS |
|
Style Transfer (F32)
|
100% |
1227
1.61 IPS |
|
Style Transfer (F16)
|
100% |
1099
1.45 IPS |
|
Style Transfer (I8)
|
98% |
2790
3.67 IPS |
|
Image Super-Resolution (F32)
|
100% |
437
15.6 IPS |
|
Image Super-Resolution (F16)
|
100% |
423
15.1 IPS |
|
Image Super-Resolution (I8)
|
98% |
970
34.6 IPS |
|
Text Classification (F32)
|
100% |
286
410.4 IPS |
|
Text Classification (F16)
|
100% |
287
412.0 IPS |
|
Text Classification (I8)
|
92% |
215
308.8 IPS |
|
Machine Translation (F32)
|
100% |
491
9.03 IPS |
|
Machine Translation (F16)
|
100% |
501
9.22 IPS |
|
Machine Translation (I8)
|
64% |
241
4.44 IPS |