Geekbench ML Score

393
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date June 13 2021 02:07 AM
Views 1

System Information

System Information
Operating System Android 11
Model Xiaomi M2012K11AG
Model IDXiaomi M2012K11AG
Motherboard alioth
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 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 3.19 GHz
Memory Information
Size 5.48 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 371
39.8 IPS
 
Image Classification (F16)
100% 371
39.7 IPS
 
Image Classification (I8)
81% 212
22.7 IPS
 
Image Segmentation (F32)
100% 554
3.42 IPS
 
Image Segmentation (F16)
100% 570
3.52 IPS
 
Image Segmentation (I8)
89% 805
4.97 IPS
 
Pose Estimation (F32)
100% 267
1.08 IPS
 
Pose Estimation (F16)
100% 267
1.08 IPS
 
Pose Estimation (I8)
80% 224
0.90 IPS
 
Object Detection (F32)
100% 343
12.0 IPS
 
Object Detection (F16)
100% 388
13.6 IPS
 
Object Detection (I8)
52% 279
9.81 IPS
 
Face Detection (F32)
100% 595
6.84 IPS
 
Face Detection (F16)
100% 583
6.70 IPS
 
Face Detection (I8)
75% 483
5.55 IPS
 
Text Classification (F32)
100% 329
130.0 IPS
 
Text Classification (F16)
100% 329
130.2 IPS
 
Machine Translation (F32)
100% 498
76.7 IPS
 
Machine Translation (F16)
100% 496
76.5 IPS
 

Compare

Set Baseline Geekbench 6 now available