Geekbench ML Score

2181
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 22 2022 02:14 PM
Views 2

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% 519
55.6 IPS
 
Image Classification (F16)
100% 6847
733.7 IPS
 
Image Classification (I8)
79% 11334
1.21 KIPS
 
Image Segmentation (F32)
100% 601
3.71 IPS
 
Image Segmentation (F16)
96% 10551
65.2 IPS
 
Image Segmentation (I8)
89% 29895
184.7 IPS
 
Pose Estimation (F32)
100% 453
1.83 IPS
 
Pose Estimation (F16)
100% 5815
23.5 IPS
 
Pose Estimation (I8)
80% 13338
54.0 IPS
 
Object Detection (F32)
100% 388
13.6 IPS
 
Object Detection (F16)
100% 1592
55.9 IPS
 
Object Detection (I8)
50% 1880
66.0 IPS
 
Face Detection (F32)
100% 749
8.60 IPS
 
Face Detection (F16)
98% 11411
131.1 IPS
 
Face Detection (I8)
75% 24620
282.9 IPS
 
Text Classification (F32)
100% 68
27.0 IPS
 
Text Classification (F16)
100% 1296
512.4 IPS
 
Machine Translation (F32)
100% 688
106.1 IPS
 
Machine Translation (F16)
100% 689
106.2 IPS
 

Compare

Set Baseline Geekbench 6 now available