Geekbench ML Score

2223
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 23 2022 11:05 AM
Views 3

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 11.15 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 485
51.9 IPS
 
Image Classification (F16)
100% 6775
725.9 IPS
 
Image Classification (I8)
79% 11147
1.19 KIPS
 
Image Segmentation (F32)
100% 593
3.66 IPS
 
Image Segmentation (F16)
96% 11192
69.1 IPS
 
Image Segmentation (I8)
89% 33690
208.1 IPS
 
Pose Estimation (F32)
100% 454
1.84 IPS
 
Pose Estimation (F16)
100% 5858
23.7 IPS
 
Pose Estimation (I8)
80% 13260
53.7 IPS
 
Object Detection (F32)
100% 400
14.0 IPS
 
Object Detection (F16)
100% 1626
57.1 IPS
 
Object Detection (I8)
50% 1867
65.5 IPS
 
Face Detection (F32)
100% 820
9.42 IPS
 
Face Detection (F16)
98% 13108
150.6 IPS
 
Face Detection (I8)
75% 24354
279.8 IPS
 
Text Classification (F32)
100% 70
27.6 IPS
 
Text Classification (F16)
100% 1282
507.0 IPS
 
Machine Translation (F32)
100% 688
106.1 IPS
 
Machine Translation (F16)
100% 690
106.4 IPS
 

Compare

Set Baseline Geekbench 6 now available