Geekbench ML Score

2006
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 26 2023 03:30 PM
Views 1

System Information

System Information
Operating System Android 13
Model Google Pixel 7 Pro
Model IDGoogle Pixel 7 Pro
Motherboard cheetah
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 @ 2.35 GHz
Cluster 32 Cores @ 2.85 GHz
Memory Information
Size 11.17 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 482
51.7 IPS
 
Image Classification (F16)
100% 5761
617.3 IPS
 
Image Classification (I8)
79% 8662
928.1 IPS
 
Image Segmentation (F32)
100% 577
3.56 IPS
 
Image Segmentation (F16)
100% 8910
55.0 IPS
 
Image Segmentation (I8)
89% 28855
178.2 IPS
 
Pose Estimation (F32)
100% 454
1.84 IPS
 
Pose Estimation (F16)
100% 4512
18.3 IPS
 
Pose Estimation (I8)
80% 10015
40.5 IPS
 
Object Detection (F32)
100% 415
14.6 IPS
 
Object Detection (F16)
100% 1535
53.9 IPS
 
Object Detection (I8)
50% 1770
62.1 IPS
 
Face Detection (F32)
100% 815
9.36 IPS
 
Face Detection (F16)
98% 10585
121.6 IPS
 
Face Detection (I8)
75% 21413
246.0 IPS
 
Text Classification (F32)
100% 76
30.0 IPS
 
Text Classification (F16)
100% 1036
409.8 IPS
 
Machine Translation (F32)
100% 685
105.5 IPS
 
Machine Translation (F16)
100% 679
104.7 IPS
 

Compare

Set Baseline Geekbench 6 now available