Geekbench ML Score

438
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 25 2023 10:29 AM
Views 1

System Information

System Information
Operating System Android 13
Model motorola motorola one 5G ace
Model IDmotorola motorola one 5G ace
Motherboard lito
Governorschedutil
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3341 revision 0
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.21 GHz
Memory Information
Size 5.33 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 321
34.3 IPS
 
Image Classification (F16)
100% 422
45.2 IPS
 
Image Classification (I8)
80% 1210
129.6 IPS
 
Image Segmentation (F32)
100% 606
3.75 IPS
 
Image Segmentation (F16)
100% 760
4.70 IPS
 
Image Segmentation (I8)
89% 3009
18.6 IPS
 
Pose Estimation (F32)
100% 156
0.63 IPS
 
Pose Estimation (F16)
100% 360
1.46 IPS
 
Pose Estimation (I8)
80% 1352
5.47 IPS
 
Object Detection (F32)
100% 371
13.0 IPS
 
Object Detection (F16)
100% 479
16.8 IPS
 
Object Detection (I8)
52% 841
29.5 IPS
 
Face Detection (F32)
100% 415
4.76 IPS
 
Face Detection (F16)
97% 491
5.65 IPS
 
Face Detection (I8)
75% 2270
26.1 IPS
 
Text Classification (F32)
54% 36
14.4 IPS
 
Text Classification (F16)
54% 32
12.8 IPS
 
Machine Translation (F32)
100% 340
52.5 IPS
 
Machine Translation (F16)
100% 338
52.0 IPS
 

Compare

Set Baseline Geekbench 6 now available