Geekbench ML Score

319
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

User aaaaaaaaaa
Upload Date October 28 2021 11:00 AM
Views 4

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 CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 136
14.6 IPS
 
Image Classification (F16)
100% 125
13.4 IPS
 
Image Classification (I8)
81% 202
21.6 IPS
 
Image Segmentation (F32)
100% 515
3.18 IPS
 
Image Segmentation (F16)
100% 319
1.97 IPS
 
Image Segmentation (I8)
89% 729
4.50 IPS
 
Pose Estimation (F32)
100% 259
1.05 IPS
 
Pose Estimation (F16)
100% 244
0.99 IPS
 
Pose Estimation (I8)
80% 230
0.93 IPS
 
Object Detection (F32)
100% 148
5.20 IPS
 
Object Detection (F16)
100% 152
5.34 IPS
 
Object Detection (I8)
52% 298
10.4 IPS
 
Face Detection (F32)
100% 558
6.41 IPS
 
Face Detection (F16)
100% 549
6.31 IPS
 
Face Detection (I8)
75% 478
5.49 IPS
 
Text Classification (F32)
100% 453
179.2 IPS
 
Text Classification (F16)
100% 417
164.8 IPS
 
Machine Translation (F32)
100% 595
91.7 IPS
 
Machine Translation (F16)
100% 594
91.6 IPS
 

Compare

Set Baseline Geekbench 6 now available