Geekbench ML Score

359
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 26 2022 02:16 AM
Views 2

System Information

System Information
Operating System Android 12
Model OnePlus DN2103
Model IDOnePlus DN2103
Motherboard k6893v1_64
CPU Information
Name ARM MT6893Z_A/CZA
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 0
Base Frequency 2.00 GHz
Cluster 14 Cores @ 2.00 GHz
Cluster 23 Cores @ 2.60 GHz
Cluster 31 Core @ 3.00 GHz
Memory Information
Size 7.32 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 270
29.0 IPS
 
Image Classification (F16)
100% 236
25.3 IPS
 
Image Classification (I8)
81% 192
20.5 IPS
 
Image Segmentation (F32)
100% 582
3.60 IPS
 
Image Segmentation (F16)
100% 587
3.63 IPS
 
Image Segmentation (I8)
89% 696
4.30 IPS
 
Pose Estimation (F32)
100% 247
1.00 IPS
 
Pose Estimation (F16)
100% 253
1.02 IPS
 
Pose Estimation (I8)
80% 176
0.71 IPS
 
Object Detection (F32)
100% 314
11.0 IPS
 
Object Detection (F16)
100% 301
10.5 IPS
 
Object Detection (I8)
52% 283
9.92 IPS
 
Face Detection (F32)
100% 559
6.42 IPS
 
Face Detection (F16)
100% 588
6.75 IPS
 
Face Detection (I8)
75% 425
4.89 IPS
 
Text Classification (F32)
100% 335
132.3 IPS
 
Text Classification (F16)
100% 323
127.8 IPS
 
Machine Translation (F32)
100% 492
75.8 IPS
 
Machine Translation (F16)
100% 575
88.6 IPS
 

Compare

Set Baseline Geekbench 6 now available