Geekbench ML Score

255
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 06 2022 01:02 PM
Views 1

System Information

System Information
Operating System Android 12
Model samsung SM-T735N
Model IDsamsung SM-T735N
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 3.35 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 135
14.5 IPS
 
Image Classification (F16)
100% 146
15.6 IPS
 
Image Classification (I8)
81% 179
19.2 IPS
 
Image Segmentation (F32)
100% 414
2.56 IPS
 
Image Segmentation (F16)
100% 408
2.52 IPS
 
Image Segmentation (I8)
89% 614
3.80 IPS
 
Pose Estimation (F32)
100% 143
0.58 IPS
 
Pose Estimation (F16)
100% 142
0.57 IPS
 
Pose Estimation (I8)
80% 152
0.62 IPS
 
Object Detection (F32)
100% 217
7.62 IPS
 
Object Detection (F16)
100% 234
8.23 IPS
 
Object Detection (I8)
52% 240
8.42 IPS
 
Face Detection (F32)
100% 351
4.03 IPS
 
Face Detection (F16)
100% 346
3.97 IPS
 
Face Detection (I8)
75% 395
4.54 IPS
 
Text Classification (F32)
100% 285
112.8 IPS
 
Text Classification (F16)
100% 285
112.9 IPS
 
Machine Translation (F32)
100% 305
47.0 IPS
 
Machine Translation (F16)
100% 333
51.3 IPS
 

Compare

Set Baseline Geekbench 6 now available