Geekbench ML Score

215
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 06 2022 03:47 AM
Views 2

System Information

System Information
Operating System Android 12
Model rockchip BlueBerry
Model IDrockchip BlueBerry
Motherboard rk30sdk
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3333 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.21 GHz
Memory Information
Size 7.49 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 164
17.6 IPS
 
Image Classification (F16)
100% 142
15.2 IPS
 
Image Classification (I8)
81% 186
19.9 IPS
 
Image Segmentation (F32)
100% 268
1.65 IPS
 
Image Segmentation (F16)
100% 252
1.56 IPS
 
Image Segmentation (I8)
89% 341
2.11 IPS
 
Pose Estimation (F32)
100% 176
0.71 IPS
 
Pose Estimation (F16)
100% 170
0.69 IPS
 
Pose Estimation (I8)
80% 56
0.22 IPS
 
Object Detection (F32)
100% 152
5.34 IPS
 
Object Detection (F16)
100% 150
5.25 IPS
 
Object Detection (I8)
52% 224
7.87 IPS
 
Face Detection (F32)
100% 248
2.85 IPS
 
Face Detection (F16)
100% 240
2.76 IPS
 
Face Detection (I8)
75% 254
2.92 IPS
 
Text Classification (F32)
100% 454
179.7 IPS
 
Text Classification (F16)
100% 454
179.5 IPS
 
Machine Translation (F32)
100% 318
49.1 IPS
 
Machine Translation (F16)
100% 263
40.6 IPS
 

Compare

Set Baseline Geekbench 6 now available