Geekbench ML Score

395
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date June 10 2023 09:11 PM
Views 2

System Information

System Information
Operating System Android 11
Model Xiaomi Redmi Note 8 Pro
Model IDXiaomi Redmi Note 8 Pro
Motherboard begonia
CPU Information
Name ARM MT6785V/CC
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.05 GHz
Memory Information
Size 5.50 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 321
34.4 IPS
 
Image Classification (F16)
100% 523
56.0 IPS
 
Image Classification (I8)
81% 1054
112.9 IPS
 
Image Segmentation (F32)
100% 334
2.06 IPS
 
Image Segmentation (F16)
100% 401
2.48 IPS
 
Image Segmentation (I8)
77% 1834
11.3 IPS
 
Pose Estimation (F32)
100% 247
1.00 IPS
 
Pose Estimation (F16)
100% 393
1.59 IPS
 
Pose Estimation (I8)
80% 775
3.13 IPS
 
Object Detection (F32)
100% 330
11.6 IPS
 
Object Detection (F16)
99% 481
16.9 IPS
 
Object Detection (I8)
53% 607
21.3 IPS
 
Face Detection (F32)
25% 121
1.39 IPS
 
Face Detection (F16)
24% 394
4.53 IPS
 
Face Detection (I8)
75% 1317
15.1 IPS
 
Text Classification (F32)
100% 158
62.7 IPS
 
Text Classification (F16)
100% 162
64.2 IPS
 
Machine Translation (F32)
100% 208
32.0 IPS
 
Machine Translation (F16)
100% 211
32.5 IPS
 

Compare

Set Baseline Geekbench 6 now available