Geekbench ML Score

1202
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 16 2022 09:57 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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 691
74.0 IPS
 
Image Classification (F16)
100% 4931
528.4 IPS
 
Image Classification (I8)
79% 9282
994.5 IPS
 
Image Segmentation (F32)
100% 1128
6.96 IPS
 
Image Segmentation (F16)
100% 223
1.38 IPS
 
Image Segmentation (I8)
89% 22380
138.2 IPS
 
Pose Estimation (F32)
100% 744
3.01 IPS
 
Pose Estimation (F16)
80% 4561
18.5 IPS
 
Pose Estimation (I8)
80% 11395
46.1 IPS
 
Object Detection (F32)
100% 572
20.1 IPS
 
Object Detection (F16)
100% 95
3.34 IPS
 
Object Detection (I8)
50% 1618
56.8 IPS
 
Face Detection (F32)
100% 1461
16.8 IPS
 
Face Detection (F16)
100% 524
6.02 IPS
 
Face Detection (I8)
75% 14832
170.4 IPS
 
Text Classification (F32)
100% 162
64.1 IPS
 
Text Classification (F16)
100% 72
28.5 IPS
 
Machine Translation (F32)
100% 642
98.9 IPS
 
Machine Translation (F16)
100% 643
99.1 IPS
 

Compare

Set Baseline Geekbench 6 now available