Geekbench ML Score

1734
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 07 2021 03:57 AM
Views 2

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 11.21 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 689
73.8 IPS
 
Image Classification (F16)
100% 5576
597.5 IPS
 
Image Classification (I8)
79% 9409
1.01 KIPS
 
Image Segmentation (F32)
100% 1175
7.26 IPS
 
Image Segmentation (F16)
100% 259
1.60 IPS
 
Image Segmentation (I8)
89% 25551
157.8 IPS
 
Pose Estimation (F32)
100% 763
3.09 IPS
 
Pose Estimation (F16)
80% 5346
21.6 IPS
 
Pose Estimation (I8)
80% 13387
54.2 IPS
 
Object Detection (F32)
100% 609
21.4 IPS
 
Object Detection (F16)
100% 1568
55.0 IPS
 
Object Detection (I8)
50% 1805
63.3 IPS
 
Face Detection (F32)
100% 1674
19.2 IPS
 
Face Detection (F16)
97% 5973
68.6 IPS
 
Face Detection (I8)
75% 16981
195.1 IPS
 
Text Classification (F32)
100% 202
80.0 IPS
 
Text Classification (F16)
100% 83
32.9 IPS
 
Machine Translation (F32)
100% 686
105.8 IPS
 
Machine Translation (F16)
100% 681
104.9 IPS
 

Compare

Set Baseline Geekbench 6 now available