Geekbench ML Score

1288
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 14 2022 02:47 PM
Views 1

System Information

System Information
Operating System Android 12
Model Google Pixel 6 Pro
Model IDGoogle Pixel 6 Pro
Motherboard raven
Governorsched_pixel
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 22 Cores @ 2.25 GHz
Cluster 32 Cores @ 2.80 GHz
Memory Information
Size 11.27 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 700
75.0 IPS
 
Image Classification (F16)
100% 5636
603.9 IPS
 
Image Classification (I8)
79% 10201
1.09 KIPS
 
Image Segmentation (F32)
100% 1132
6.99 IPS
 
Image Segmentation (F16)
100% 257
1.59 IPS
 
Image Segmentation (I8)
89% 25529
157.7 IPS
 
Pose Estimation (F32)
100% 751
3.04 IPS
 
Pose Estimation (F16)
80% 5352
21.7 IPS
 
Pose Estimation (I8)
80% 13395
54.2 IPS
 
Object Detection (F32)
100% 587
20.6 IPS
 
Object Detection (F16)
100% 95
3.34 IPS
 
Object Detection (I8)
50% 1804
63.3 IPS
 
Face Detection (F32)
100% 1415
16.3 IPS
 
Face Detection (F16)
100% 513
5.89 IPS
 
Face Detection (I8)
75% 16861
193.7 IPS
 
Text Classification (F32)
100% 165
65.4 IPS
 
Text Classification (F16)
100% 81
32.2 IPS
 
Machine Translation (F32)
100% 684
105.4 IPS
 
Machine Translation (F16)
100% 684
105.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download