Geekbench ML Score

332
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 14 2022 10:28 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 11.27 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 121
12.9 IPS
 
Image Classification (F16)
100% 117
12.5 IPS
 
Image Classification (I8)
81% 237
25.4 IPS
 
Image Segmentation (F32)
100% 279
1.72 IPS
 
Image Segmentation (F16)
100% 498
3.07 IPS
 
Image Segmentation (I8)
89% 799
4.94 IPS
 
Pose Estimation (F32)
100% 258
1.05 IPS
 
Pose Estimation (F16)
100% 244
0.99 IPS
 
Pose Estimation (I8)
80% 242
0.98 IPS
 
Object Detection (F32)
100% 140
4.93 IPS
 
Object Detection (F16)
100% 138
4.85 IPS
 
Object Detection (I8)
52% 323
11.3 IPS
 
Face Detection (F32)
100% 623
7.16 IPS
 
Face Detection (F16)
100% 604
6.94 IPS
 
Face Detection (I8)
75% 538
6.18 IPS
 
Text Classification (F32)
100% 518
205.0 IPS
 
Text Classification (F16)
100% 500
197.7 IPS
 
Machine Translation (F32)
100% 670
103.3 IPS
 
Machine Translation (F16)
100% 677
104.3 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download