Geekbench ML Score

210
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 24 2022 03:58 PM
Views 1

System Information

System Information
Operating System Android 12
Model vivo I2208
Model IDvivo I2208
Motherboard holi
Governorschedutil
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.02 GHz
Memory Information
Size 5.39 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 275
29.4 IPS
 
Image Classification (F16)
100% 371
39.7 IPS
 
Image Classification (I8)
81% 184
19.7 IPS
 
Image Segmentation (F32)
100% 609
3.76 IPS
 
Image Segmentation (F16)
100% 850
5.25 IPS
 
Image Segmentation (I8)
89% 347
2.14 IPS
 
Pose Estimation (F32)
100% 123
0.50 IPS
 
Pose Estimation (F16)
100% 253
1.02 IPS
 
Pose Estimation (I8)
80% 55
0.22 IPS
 
Object Detection (F32)
100% 245
8.60 IPS
 
Object Detection (F16)
100% 313
11.0 IPS
 
Object Detection (I8)
52% 225
7.90 IPS
 
Face Detection (F32)
100% 417
4.79 IPS
 
Face Detection (F16)
97% 661
7.60 IPS
 
Face Detection (I8)
75% 274
3.15 IPS
 
Text Classification (F32)
100% 3
1.34 IPS
 
Text Classification (F16)
100% 54
21.3 IPS
 
Machine Translation (F32)
100% 331
51.1 IPS
 
Machine Translation (F16)
100% 331
51.0 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download