Huawei Mate 20 Pro
Geekbench ML Score
1019
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | November 04 2022 11:43 PM |
| Views | 1 |
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% |
615
65.9 IPS |
|
|
Image Classification (F16)
|
100% |
1164
124.8 IPS |
|
|
Image Classification (I8)
|
80% |
1111
119.0 IPS |
|
|
Image Segmentation (F32)
|
100% |
1551
9.58 IPS |
|
|
Image Segmentation (F16)
|
100% |
3022
18.7 IPS |
|
|
Image Segmentation (I8)
|
89% |
3132
19.3 IPS |
|
|
Pose Estimation (F32)
|
100% |
326
1.32 IPS |
|
|
Pose Estimation (F16)
|
100% |
1694
6.85 IPS |
|
|
Pose Estimation (I8)
|
80% |
1705
6.90 IPS |
|
|
Object Detection (F32)
|
100% |
461
16.2 IPS |
|
|
Object Detection (F16)
|
100% |
723
25.4 IPS |
|
|
Object Detection (I8)
|
54% |
513
18.0 IPS |
|
|
Face Detection (F32)
|
100% |
1289
14.8 IPS |
|
|
Face Detection (F16)
|
97% |
2600
29.9 IPS |
|
|
Face Detection (I8)
|
75% |
2325
26.7 IPS |
|
|
Text Classification (F32)
|
100% |
711
281.4 IPS |
|
|
Text Classification (F16)
|
98% |
925
365.8 IPS |
|
|
Machine Translation (F32)
|
100% |
385
59.3 IPS |
|
|
Machine Translation (F16)
|
100% |
392
60.3 IPS |
