HUAWEI MAR-LX1B
Geekbench ML Score
109
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | November 03 2021 04:11 PM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | Android 10 |
| Model | HUAWEI MAR-LX1B |
| Model ID | HUAWEI MAR-LX1B |
| Motherboard | MAR |
| CPU Information | |
|---|---|
| Name | ARM Hisilicon |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3337 revision 2 |
| Base Frequency | 1.71 GHz |
| Cluster 1 | 4 Cores @ 1.71 GHz |
| Cluster 2 | 4 Cores @ 2.19 GHz |
| Memory Information | |
|---|---|
| Size | 5.56 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
64
6.81 IPS |
|
|
Image Classification (F16)
|
100% |
63
6.74 IPS |
|
|
Image Classification (I8)
|
81% |
92
9.82 IPS |
|
|
Image Segmentation (F32)
|
100% |
150
0.93 IPS |
|
|
Image Segmentation (F16)
|
100% |
144
0.89 IPS |
|
|
Image Segmentation (I8)
|
89% |
389
2.41 IPS |
|
|
Pose Estimation (F32)
|
100% |
74
0.30 IPS |
|
|
Pose Estimation (F16)
|
100% |
73
0.29 IPS |
|
|
Pose Estimation (I8)
|
80% |
114
0.46 IPS |
|
|
Object Detection (F32)
|
100% |
95
3.33 IPS |
|
|
Object Detection (F16)
|
100% |
98
3.44 IPS |
|
|
Object Detection (I8)
|
52% |
138
4.86 IPS |
|
|
Face Detection (F32)
|
100% |
141
1.62 IPS |
|
|
Face Detection (F16)
|
100% |
135
1.55 IPS |
|
|
Face Detection (I8)
|
75% |
215
2.47 IPS |
|
|
Text Classification (F32)
|
100% |
100
39.7 IPS |
|
|
Text Classification (F16)
|
100% |
112
44.1 IPS |
|
|
Machine Translation (F32)
|
100% |
73
11.2 IPS |
|
|
Machine Translation (F16)
|
100% |
73
11.3 IPS |
