Geekbench ML Score

124
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 07:49 AM
Views 2

System Information

System Information
Operating System Android 10
Model samsung SM-T835N
Model IDsamsung SM-T835N
Motherboard msm8998
Governorinteractive
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 10 part 2048 revision 1
Base Frequency 1.90 GHz
Cluster 14 Cores @ 1.90 GHz
Cluster 24 Cores @ 2.36 GHz
Memory Information
Size 5.46 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 79
8.45 IPS
 
Image Classification (F16)
100% 79
8.47 IPS
 
Image Classification (I8)
81% 134
14.4 IPS
 
Image Segmentation (F32)
100% 174
1.07 IPS
 
Image Segmentation (F16)
100% 184
1.14 IPS
 
Image Segmentation (I8)
89% 229
1.41 IPS
 
Pose Estimation (F32)
100% 73
0.30 IPS
 
Pose Estimation (F16)
100% 70
0.28 IPS
 
Pose Estimation (I8)
80% 43
0.17 IPS
 
Object Detection (F32)
100% 130
4.55 IPS
 
Object Detection (F16)
100% 104
3.64 IPS
 
Object Detection (I8)
52% 166
5.81 IPS
 
Face Detection (F32)
100% 134
1.54 IPS
 
Face Detection (F16)
100% 145
1.66 IPS
 
Face Detection (I8)
75% 179
2.06 IPS
 
Text Classification (F32)
100% 177
70.1 IPS
 
Text Classification (F16)
100% 177
70.0 IPS
 
Machine Translation (F32)
100% 143
22.0 IPS
 
Machine Translation (F16)
100% 143
22.0 IPS
 

Compare

Set Baseline