Geekbench ML Score

320
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

User Dragon0118
Upload Date December 09 2022 06:20 AM
Views 3

System Information

System Information
Operating System Android 10
Model HUAWEI LIO-L29
Model IDHUAWEI LIO-L29
Motherboard LIO
CPU Information
Name vendor
Topology 1 Processor, 8 Cores
Identifier ARM implementer 72 architecture 8 variant 3 part 3392 revision 0
Base Frequency 1.86 GHz
Cluster 14 Cores @ 1.86 GHz
Cluster 22 Cores @ 2.09 GHz
Cluster 32 Cores @ 2.86 GHz
Memory Information
Size 7.34 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 202
21.6 IPS
 
Image Classification (F16)
100% 212
22.8 IPS
 
Image Classification (I8)
81% 234
25.1 IPS
 
Image Segmentation (F32)
100% 368
2.27 IPS
 
Image Segmentation (F16)
100% 387
2.39 IPS
 
Image Segmentation (I8)
89% 3142
19.4 IPS
 
Pose Estimation (F32)
100% 209
0.85 IPS
 
Pose Estimation (F16)
100% 212
0.86 IPS
 
Pose Estimation (I8)
80% 69
0.28 IPS
 
Object Detection (F32)
100% 195
6.84 IPS
 
Object Detection (F16)
100% 1014
35.6 IPS
 
Object Detection (I8)
52% 292
10.3 IPS
 
Face Detection (F32)
100% 248
2.85 IPS
 
Face Detection (F16)
100% 262
3.01 IPS
 
Face Detection (I8)
75% 324
3.72 IPS
 
Text Classification (F32)
100% 601
237.8 IPS
 
Text Classification (F16)
100% 195
77.3 IPS
 
Machine Translation (F32)
100% 459
70.8 IPS
 
Machine Translation (F16)
100% 458
70.6 IPS
 

Compare

Set Baseline