Huawei Mate 20 Pro
Geekbench ML Score
1043
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | July 16 2022 06:25 PM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | Android 10 |
| Model | Huawei Mate 20 Pro |
| Model ID | HUAWEI LYA-L29 |
| Motherboard | LYA |
| CPU Information | |
|---|---|
| Name | vendor |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 72 architecture 8 variant 1 part 3392 revision 0 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 4 Cores @ 1.80 GHz |
| Cluster 2 | 2 Cores @ 1.92 GHz |
| Cluster 3 | 2 Cores @ 2.60 GHz |
| Memory Information | |
|---|---|
| Size | 5.42 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
609
65.3 IPS |
|
|
Image Classification (F16)
|
100% |
1218
130.5 IPS |
|
|
Image Classification (I8)
|
80% |
1130
121.0 IPS |
|
|
Image Segmentation (F32)
|
100% |
1592
9.84 IPS |
|
|
Image Segmentation (F16)
|
100% |
3248
20.1 IPS |
|
|
Image Segmentation (I8)
|
89% |
3174
19.6 IPS |
|
|
Pose Estimation (F32)
|
100% |
314
1.27 IPS |
|
|
Pose Estimation (F16)
|
100% |
1721
6.96 IPS |
|
|
Pose Estimation (I8)
|
80% |
1674
6.77 IPS |
|
|
Object Detection (F32)
|
100% |
493
17.3 IPS |
|
|
Object Detection (F16)
|
100% |
726
25.5 IPS |
|
|
Object Detection (I8)
|
54% |
717
25.2 IPS |
|
|
Face Detection (F32)
|
100% |
1266
14.5 IPS |
|
|
Face Detection (F16)
|
97% |
2643
30.4 IPS |
|
|
Face Detection (I8)
|
75% |
2315
26.6 IPS |
|
|
Text Classification (F32)
|
100% |
630
249.0 IPS |
|
|
Text Classification (F16)
|
98% |
911
360.5 IPS |
|
|
Machine Translation (F32)
|
100% |
399
61.5 IPS |
|
|
Machine Translation (F16)
|
100% |
400
61.6 IPS |
