Geekbench ML Score

1020
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 29 2021 01:30 AM
Views 2

System Information

System Information
Operating System Android 11
Model LGE LM-V700N
Model IDLGE LM-V700N
Motherboard lahaina
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 7.17 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 970
104.0 IPS
 
Image Classification (F16)
100% 1584
169.7 IPS
 
Image Classification (I8)
79% 5012
537.0 IPS
 
Image Segmentation (F32)
100% 2314
14.3 IPS
 
Image Segmentation (F16)
71% 3323
20.5 IPS
 
Image Segmentation (I8)
89% 9593
59.3 IPS
 
Pose Estimation (F32)
100% 561
2.27 IPS
 
Pose Estimation (F16)
100% 1985
8.03 IPS
 
Pose Estimation (I8)
80% 24606
99.6 IPS
 
Object Detection (F32)
100% 790
27.7 IPS
 
Object Detection (F16)
100% 1000
35.1 IPS
 
Object Detection (I8)
56% 1416
49.7 IPS
 
Face Detection (F32)
100% 448
5.14 IPS
 
Face Detection (F16)
100% 523
6.01 IPS
 
Face Detection (I8)
76% 22209
255.2 IPS
 
Text Classification (F32)
100% 8
3.30 IPS
 
Text Classification (F16)
46% 7
2.84 IPS
 
Machine Translation (F32)
100% 528
81.3 IPS
 
Machine Translation (F16)
100% 552
85.1 IPS
 

Compare

Set Baseline Geekbench 6 now available