Geekbench ML Score

50
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date March 19 2023 02:53 AM
Views 2

System Information

System Information
Operating System Android 12
Model samsung SM-S134DL
Model IDsamsung SM-S134DL
Motherboard a03su
CPU Information
Name ARM MT6765V/CB
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3331 revision 4
Base Frequency 2.30 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.30 GHz
Memory Information
Size 2.71 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 36
3.85 IPS
 
Image Classification (F16)
100% 35
3.80 IPS
 
Image Classification (I8)
81% 67
7.18 IPS
 
Image Segmentation (F32)
100% 89
0.55 IPS
 
Image Segmentation (F16)
100% 89
0.55 IPS
 
Image Segmentation (I8)
89% 123
0.76 IPS
 
Pose Estimation (F32)
100% 36
0.15 IPS
 
Pose Estimation (F16)
100% 36
0.14 IPS
 
Pose Estimation (I8)
80% 20
0.08 IPS
 
Object Detection (F32)
100% 52
1.82 IPS
 
Object Detection (F16)
100% 51
1.80 IPS
 
Object Detection (I8)
52% 85
2.97 IPS
 
Face Detection (F32)
100% 76
0.88 IPS
 
Face Detection (F16)
100% 76
0.88 IPS
 
Face Detection (I8)
75% 95
1.09 IPS
 
Text Classification (F32)
100% 81
32.0 IPS
 
Text Classification (F16)
100% 81
32.0 IPS
 
Machine Translation (F32)
100% 12
1.90 IPS
 
Machine Translation (F16)
100% 12
1.90 IPS
 

Compare

Set Baseline Geekbench 6 now available