Xiaomi Mi A2
Geekbench ML Score
127
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | June 12 2021 06:36 PM |
| Views | 3 |
System Information
| System Information | |
|---|---|
| Operating System | Android 10 |
| Model | Xiaomi Mi A2 |
| Model ID | Xiaomi Mi A2 |
| Motherboard | sdm660 |
| Governor | interactive |
| CPU Information | |
|---|---|
| Name | Qualcomm Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 81 architecture 8 variant 10 part 2048 revision 2 |
| Base Frequency | 1.84 GHz |
| Cluster 1 | 4 Cores @ 1.84 GHz |
| Cluster 2 | 4 Cores @ 2.21 GHz |
| Memory Information | |
|---|---|
| Size | 3.65 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
76
8.10 IPS |
|
|
Image Classification (F16)
|
100% |
72
7.75 IPS |
|
|
Image Classification (I8)
|
81% |
127
13.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
184
1.14 IPS |
|
|
Image Segmentation (F16)
|
100% |
187
1.15 IPS |
|
|
Image Segmentation (I8)
|
89% |
405
2.50 IPS |
|
|
Pose Estimation (F32)
|
100% |
64
0.26 IPS |
|
|
Pose Estimation (F16)
|
100% |
66
0.27 IPS |
|
|
Pose Estimation (I8)
|
80% |
104
0.42 IPS |
|
|
Object Detection (F32)
|
100% |
131
4.61 IPS |
|
|
Object Detection (F16)
|
100% |
116
4.08 IPS |
|
|
Object Detection (I8)
|
52% |
173
6.09 IPS |
|
|
Face Detection (F32)
|
100% |
175
2.01 IPS |
|
|
Face Detection (F16)
|
100% |
169
1.94 IPS |
|
|
Face Detection (I8)
|
75% |
255
2.92 IPS |
|
|
Text Classification (F32)
|
100% |
118
46.5 IPS |
|
|
Text Classification (F16)
|
100% |
113
44.9 IPS |
|
|
Machine Translation (F32)
|
100% |
94
14.5 IPS |
|
|
Machine Translation (F16)
|
100% |
94
14.5 IPS |
