Geekbench ML Score

420
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 14 2022 11:01 AM
Views 1

System Information

System Information
Operating System Android 12
Model Xiaomi M2011K2G
Model IDXiaomi M2011K2G
Motherboard venus
Governorschedutil
CPU Information
Name ARM Venus
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 7.08 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 442
47.4 IPS
 
Image Classification (F16)
100% 351
37.6 IPS
 
Image Classification (I8)
81% 196
21.0 IPS
 
Image Segmentation (F32)
100% 611
3.78 IPS
 
Image Segmentation (F16)
100% 609
3.76 IPS
 
Image Segmentation (I8)
89% 832
5.14 IPS
 
Pose Estimation (F32)
100% 266
1.08 IPS
 
Pose Estimation (F16)
100% 267
1.08 IPS
 
Pose Estimation (I8)
80% 239
0.97 IPS
 
Object Detection (F32)
100% 434
15.2 IPS
 
Object Detection (F16)
100% 413
14.5 IPS
 
Object Detection (I8)
52% 279
9.78 IPS
 
Face Detection (F32)
100% 600
6.89 IPS
 
Face Detection (F16)
100% 597
6.86 IPS
 
Face Detection (I8)
75% 484
5.56 IPS
 
Text Classification (F32)
100% 330
130.5 IPS
 
Text Classification (F16)
100% 326
129.0 IPS
 
Machine Translation (F32)
100% 689
106.2 IPS
 
Machine Translation (F16)
100% 699
107.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download