Upload Date | July 04 2024 07:06 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Xiaomi 2206123SC |
Model ID | Xiaomi 2206123SC |
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 | 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 | 7.01 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
388
72.7 IPS |
|
Image Classification (F16)
|
100% |
382
71.5 IPS |
|
Image Classification (I8)
|
97% |
644
120.5 IPS |
|
Image Segmentation (F32)
|
100% |
484
8.08 IPS |
|
Image Segmentation (F16)
|
100% |
478
7.98 IPS |
|
Image Segmentation (I8)
|
98% |
552
9.21 IPS |
|
Pose Estimation (F32)
|
100% |
974
1.18 IPS |
|
Pose Estimation (F16)
|
100% |
970
1.17 IPS |
|
Pose Estimation (I8)
|
100% |
3703
4.48 IPS |
|
Object Detection (F32)
|
100% |
373
27.9 IPS |
|
Object Detection (F16)
|
100% |
374
27.9 IPS |
|
Object Detection (I8)
|
61% |
812
60.6 IPS |
|
Face Detection (F32)
|
100% |
874
10.4 IPS |
|
Face Detection (F16)
|
100% |
881
10.5 IPS |
|
Face Detection (I8)
|
86% |
1471
17.5 IPS |
|
Depth Estimation (F32)
|
100% |
926
7.18 IPS |
|
Depth Estimation (F16)
|
100% |
908
7.04 IPS |
|
Depth Estimation (I8)
|
95% |
1693
13.1 IPS |
|
Style Transfer (F32)
|
100% |
1632
2.15 IPS |
|
Style Transfer (F16)
|
100% |
1726
2.27 IPS |
|
Style Transfer (I8)
|
98% |
3988
5.25 IPS |
|
Image Super-Resolution (F32)
|
100% |
520
18.6 IPS |
|
Image Super-Resolution (F16)
|
100% |
552
19.7 IPS |
|
Image Super-Resolution (I8)
|
98% |
1391
49.7 IPS |
|
Text Classification (F32)
|
100% |
409
588.4 IPS |
|
Text Classification (F16)
|
100% |
386
555.3 IPS |
|
Text Classification (I8)
|
92% |
303
434.8 IPS |
|
Machine Translation (F32)
|
100% |
817
15.0 IPS |
|
Machine Translation (F16)
|
100% |
828
15.2 IPS |
|
Machine Translation (I8)
|
64% |
321
5.91 IPS |