Xiaomi 12S Pro
Geekbench ML Score
693
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | July 27 2024 02:20 AM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | Xiaomi 12S Pro |
| Model ID | Xiaomi 2206122SC |
| 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 | 7.04 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
367
68.7 IPS |
|
|
Image Classification (F16)
|
100% |
296
55.4 IPS |
|
|
Image Classification (I8)
|
97% |
615
115.0 IPS |
|
|
Image Segmentation (F32)
|
100% |
516
8.62 IPS |
|
|
Image Segmentation (F16)
|
100% |
514
8.59 IPS |
|
|
Image Segmentation (I8)
|
98% |
619
10.3 IPS |
|
|
Pose Estimation (F32)
|
100% |
936
1.13 IPS |
|
|
Pose Estimation (F16)
|
100% |
883
1.07 IPS |
|
|
Pose Estimation (I8)
|
100% |
3606
4.37 IPS |
|
|
Object Detection (F32)
|
100% |
357
26.7 IPS |
|
|
Object Detection (F16)
|
100% |
370
27.6 IPS |
|
|
Object Detection (I8)
|
61% |
707
52.8 IPS |
|
|
Face Detection (F32)
|
100% |
758
9.01 IPS |
|
|
Face Detection (F16)
|
100% |
753
8.96 IPS |
|
|
Face Detection (I8)
|
86% |
1227
14.6 IPS |
|
|
Depth Estimation (F32)
|
100% |
803
6.23 IPS |
|
|
Depth Estimation (F16)
|
100% |
808
6.27 IPS |
|
|
Depth Estimation (I8)
|
95% |
1421
11.0 IPS |
|
|
Style Transfer (F32)
|
100% |
1477
1.94 IPS |
|
|
Style Transfer (F16)
|
100% |
1487
1.96 IPS |
|
|
Style Transfer (I8)
|
98% |
2903
3.82 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
470
16.8 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
484
17.3 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
1162
41.5 IPS |
|
|
Text Classification (F32)
|
100% |
343
492.2 IPS |
|
|
Text Classification (F16)
|
100% |
363
522.3 IPS |
|
|
Text Classification (I8)
|
92% |
265
380.4 IPS |
|
|
Machine Translation (F32)
|
100% |
716
13.2 IPS |
|
|
Machine Translation (F16)
|
100% |
726
13.4 IPS |
|
|
Machine Translation (I8)
|
64% |
305
5.61 IPS |
