Upload Date | October 06 2022 02:13 PM |
Views | 1 |
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 |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
615
65.9 IPS |
|
Image Classification (F16)
|
100% |
1251
134.1 IPS |
|
Image Classification (I8)
|
80% |
1096
117.5 IPS |
|
Image Segmentation (F32)
|
100% |
1555
9.61 IPS |
|
Image Segmentation (F16)
|
100% |
3037
18.8 IPS |
|
Image Segmentation (I8)
|
89% |
3090
19.1 IPS |
|
Pose Estimation (F32)
|
100% |
321
1.30 IPS |
|
Pose Estimation (F16)
|
100% |
1690
6.84 IPS |
|
Pose Estimation (I8)
|
80% |
1671
6.76 IPS |
|
Object Detection (F32)
|
100% |
478
16.8 IPS |
|
Object Detection (F16)
|
100% |
745
26.1 IPS |
|
Object Detection (I8)
|
54% |
600
21.0 IPS |
|
Face Detection (F32)
|
100% |
1279
14.7 IPS |
|
Face Detection (F16)
|
97% |
2645
30.4 IPS |
|
Face Detection (I8)
|
75% |
2395
27.5 IPS |
|
Text Classification (F32)
|
100% |
682
269.8 IPS |
|
Text Classification (F16)
|
98% |
837
330.9 IPS |
|
Machine Translation (F32)
|
100% |
392
60.4 IPS |
|
Machine Translation (F16)
|
100% |
391
60.2 IPS |