Geekbench ML Score

293
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 14 2021 06:45 AM
Views 1

System Information

System Information
Operating System Android 11
Model Xiaomi M2101K6P
Model IDXiaomi M2101K6P
Motherboard sweetin
Governorschedutil
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 13 part 2052 revision 14
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.30 GHz
Memory Information
Size 5.44 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 301
32.3 IPS
 
Image Classification (F16)
100% 403
43.2 IPS
 
Image Classification (I8)
80% 662
70.9 IPS
 
Image Segmentation (F32)
100% 421
2.60 IPS
 
Image Segmentation (F16)
100% 526
3.25 IPS
 
Image Segmentation (I8)
89% 1230
7.59 IPS
 
Pose Estimation (F32)
100% 152
0.61 IPS
 
Pose Estimation (F16)
100% 348
1.41 IPS
 
Pose Estimation (I8)
80% 1237
5.01 IPS
 
Object Detection (F32)
100% 252
8.86 IPS
 
Object Detection (F16)
100% 314
11.0 IPS
 
Object Detection (I8)
52% 490
17.2 IPS
 
Face Detection (F32)
100% 381
4.38 IPS
 
Face Detection (F16)
97% 444
5.11 IPS
 
Face Detection (I8)
75% 1631
18.7 IPS
 
Text Classification (F32)
54% 11
4.17 IPS
 
Text Classification (F16)
54% 12
4.56 IPS
 
Machine Translation (F32)
100% 197
30.4 IPS
 
Machine Translation (F16)
100% 196
30.2 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download