Geekbench ML Score

1586
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 04 2021 01:43 AM
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 11.21 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 641
68.7 IPS
 
Image Classification (F16)
100% 4855
520.2 IPS
 
Image Classification (I8)
79% 9705
1.04 KIPS
 
Image Segmentation (F32)
100% 1186
7.33 IPS
 
Image Segmentation (F16)
100% 223
1.37 IPS
 
Image Segmentation (I8)
89% 22437
138.6 IPS
 
Pose Estimation (F32)
100% 776
3.14 IPS
 
Pose Estimation (F16)
80% 4554
18.4 IPS
 
Pose Estimation (I8)
80% 11375
46.0 IPS
 
Object Detection (F32)
100% 580
20.3 IPS
 
Object Detection (F16)
100% 1358
47.6 IPS
 
Object Detection (I8)
50% 1556
54.6 IPS
 
Face Detection (F32)
100% 1592
18.3 IPS
 
Face Detection (F16)
97% 5126
58.9 IPS
 
Face Detection (I8)
75% 14926
171.5 IPS
 
Text Classification (F32)
100% 208
82.4 IPS
 
Text Classification (F16)
100% 73
28.9 IPS
 
Machine Translation (F32)
100% 628
96.8 IPS
 
Machine Translation (F16)
100% 629
96.9 IPS
 

Compare

Set Baseline Geekbench 6 now available