Geekbench ML Score

263
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 23 2021 03:02 AM
Views 1

System Information

System Information
Operating System Android 11
Model LG V50S ThinQ 5G
Model IDLGE LM-V510N
Motherboard msmnile
Governorschedutil
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 13 part 2052 revision 14
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 7.25 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 250
26.8 IPS
 
Image Classification (F16)
100% 229
24.5 IPS
 
Image Classification (I8)
81% 128
13.7 IPS
 
Image Segmentation (F32)
100% 397
2.45 IPS
 
Image Segmentation (F16)
100% 454
2.81 IPS
 
Image Segmentation (I8)
89% 556
3.43 IPS
 
Pose Estimation (F32)
100% 195
0.79 IPS
 
Pose Estimation (F16)
100% 184
0.75 IPS
 
Pose Estimation (I8)
80% 141
0.57 IPS
 
Object Detection (F32)
100% 239
8.37 IPS
 
Object Detection (F16)
100% 230
8.09 IPS
 
Object Detection (I8)
52% 194
6.81 IPS
 
Face Detection (F32)
100% 419
4.82 IPS
 
Face Detection (F16)
100% 416
4.77 IPS
 
Face Detection (I8)
75% 355
4.08 IPS
 
Text Classification (F32)
100% 231
91.6 IPS
 
Text Classification (F16)
100% 201
79.5 IPS
 
Machine Translation (F32)
100% 297
45.7 IPS
 
Machine Translation (F16)
100% 293
45.2 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download