Xiaomi M2102J20SI
Geekbench ML Score
346
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | December 09 2022 08:52 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | Xiaomi M2102J20SI |
| Model ID | Xiaomi M2102J20SI |
| Motherboard | msmnile |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | Qualcomm Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 81 architecture 8 variant 13 part 2052 revision 14 |
| Base Frequency | 0 MHz |
| Cluster 1 | 4 Cores @ 1.79 GHz |
| Cluster 2 | 3 Cores @ 2.42 GHz |
| Cluster 3 | 1 Core @ 2.96 GHz |
| Memory Information | |
|---|---|
| Size | 7.30 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
304
32.6 IPS |
|
|
Image Classification (F16)
|
100% |
284
30.5 IPS |
|
|
Image Classification (I8)
|
81% |
183
19.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
508
3.14 IPS |
|
|
Image Segmentation (F16)
|
100% |
486
3.00 IPS |
|
|
Image Segmentation (I8)
|
89% |
789
4.87 IPS |
|
|
Pose Estimation (F32)
|
100% |
192
0.78 IPS |
|
|
Pose Estimation (F16)
|
100% |
185
0.75 IPS |
|
|
Pose Estimation (I8)
|
80% |
189
0.76 IPS |
|
|
Object Detection (F32)
|
100% |
364
12.8 IPS |
|
|
Object Detection (F16)
|
100% |
357
12.5 IPS |
|
|
Object Detection (I8)
|
52% |
282
9.88 IPS |
|
|
Face Detection (F32)
|
100% |
554
6.36 IPS |
|
|
Face Detection (F16)
|
100% |
550
6.31 IPS |
|
|
Face Detection (I8)
|
75% |
482
5.53 IPS |
|
|
Text Classification (F32)
|
100% |
310
122.6 IPS |
|
|
Text Classification (F16)
|
100% |
307
121.4 IPS |
|
|
Machine Translation (F32)
|
100% |
417
64.3 IPS |
|
|
Machine Translation (F16)
|
100% |
403
62.0 IPS |
