Upload Date | May 17 2022 07:02 AM |
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 | NNAPI |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
241
25.9 IPS |
|
Image Classification (F16)
|
99% |
282
30.2 IPS |
|
Image Classification (I8)
|
81% |
222
23.8 IPS |
|
Image Segmentation (F32)
|
100% |
463
2.86 IPS |
|
Image Segmentation (F16)
|
100% |
460
2.84 IPS |
|
Image Segmentation (I8)
|
89% |
412
2.55 IPS |
|
Pose Estimation (F32)
|
100% |
209
0.84 IPS |
|
Pose Estimation (F16)
|
100% |
1309
5.30 IPS |
|
Pose Estimation (I8)
|
80% |
67
0.27 IPS |
|
Object Detection (F32)
|
100% |
402
14.1 IPS |
|
Object Detection (F16)
|
99% |
504
17.7 IPS |
|
Object Detection (I8)
|
52% |
270
9.47 IPS |
|
Face Detection (F32)
|
100% |
489
5.62 IPS |
|
Face Detection (F16)
|
100% |
481
5.53 IPS |
|
Face Detection (I8)
|
75% |
317
3.65 IPS |
|
Text Classification (F32)
|
100% |
566
223.9 IPS |
|
Text Classification (F16)
|
100% |
566
223.9 IPS |
|
Machine Translation (F32)
|
100% |
389
59.9 IPS |
|
Machine Translation (F16)
|
100% |
388
59.8 IPS |