Geekbench ML Score

1903
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

User hass
Upload Date October 28 2023 01:00 AM
Views 3

System Information

System Information
Operating System Android 14
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% 497
53.2 IPS
 
Image Classification (F16)
100% 7671
821.9 IPS
 
Image Classification (I8)
79% 11227
1.20 KIPS
 
Image Segmentation (F32)
100% 597
3.69 IPS
 
Image Segmentation (F16)
100% 11004
68.0 IPS
 
Image Segmentation (I8)
89% 34866
215.4 IPS
 
Pose Estimation (F32)
100% 454
1.84 IPS
 
Pose Estimation (F16)
100% 5610
22.7 IPS
 
Pose Estimation (I8)
80% 11974
48.5 IPS
 
Object Detection (F32)
100% 416
14.6 IPS
 
Object Detection (F16)
100% 1625
57.0 IPS
 
Object Detection (I8)
50% 1854
65.1 IPS
 
Face Detection (F32)
100% 782
8.98 IPS
 
Face Detection (F16)
100% 561
6.44 IPS
 
Face Detection (I8)
75% 27505
316.0 IPS
 
Text Classification (F32)
100% 87
34.4 IPS
 
Text Classification (F16)
100% 1067
422.1 IPS
 
Machine Translation (F32)
100% 706
108.8 IPS
 
Machine Translation (F16)
100% 694
107.0 IPS
 

Compare

Set Baseline Geekbench 6 now available