Geekbench ML Score

365
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 08 2022 12:11 PM
Views 1

System Information

System Information
Operating System Android 10
Model Huawei Mate 20 Pro
Model IDHUAWEI 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 14 Cores @ 1.80 GHz
Cluster 22 Cores @ 1.92 GHz
Cluster 32 Cores @ 2.60 GHz
Memory Information
Size 5.42 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 242
25.9 IPS
 
Image Classification (F16)
99% 291
31.2 IPS
 
Image Classification (I8)
81% 222
23.8 IPS
 
Image Segmentation (F32)
100% 473
2.92 IPS
 
Image Segmentation (F16)
100% 462
2.86 IPS
 
Image Segmentation (I8)
89% 411
2.54 IPS
 
Pose Estimation (F32)
100% 207
0.84 IPS
 
Pose Estimation (F16)
100% 1319
5.34 IPS
 
Pose Estimation (I8)
80% 67
0.27 IPS
 
Object Detection (F32)
100% 397
13.9 IPS
 
Object Detection (F16)
99% 516
18.1 IPS
 
Object Detection (I8)
52% 270
9.48 IPS
 
Face Detection (F32)
100% 490
5.63 IPS
 
Face Detection (F16)
100% 477
5.49 IPS
 
Face Detection (I8)
75% 318
3.65 IPS
 
Text Classification (F32)
100% 563
222.9 IPS
 
Text Classification (F16)
100% 565
223.6 IPS
 
Machine Translation (F32)
100% 390
60.0 IPS
 
Machine Translation (F16)
100% 388
59.8 IPS
 

Compare

Set Baseline