Geekbench ML Score

351
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date May 10 2024 03:17 AM
Views 1

System Information

System Information
Operating System Android 13
Model Xiaomi 11 Lite 5G NE
Model IDXiaomi 2109119DI
Motherboard lisa
Governorschedutil
CPU Information
Name ARM lisa
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.40 GHz
Memory Information
Size 5.10 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 88
16.4 IPS
 
Image Classification (F16)
100% 68
12.7 IPS
 
Image Classification (I8)
97% 236
44.1 IPS
 
Image Segmentation (F32)
100% 248
4.15 IPS
 
Image Segmentation (F16)
100% 251
4.20 IPS
 
Image Segmentation (I8)
98% 323
5.39 IPS
 
Pose Estimation (F32)
100% 402
0.49 IPS
 
Pose Estimation (F16)
100% 404
0.49 IPS
 
Pose Estimation (I8)
100% 1630
1.97 IPS
 
Object Detection (F32)
100% 189
14.1 IPS
 
Object Detection (F16)
100% 199
14.9 IPS
 
Object Detection (I8)
61% 414
30.9 IPS
 
Face Detection (F32)
100% 444
5.28 IPS
 
Face Detection (F16)
100% 436
5.18 IPS
 
Face Detection (I8)
86% 810
9.63 IPS
 
Depth Estimation (F32)
100% 432
3.35 IPS
 
Depth Estimation (F16)
100% 430
3.34 IPS
 
Depth Estimation (I8)
95% 855
6.63 IPS
 
Style Transfer (F32)
100% 701
0.92 IPS
 
Style Transfer (F16)
100% 586
0.77 IPS
 
Style Transfer (I8)
98% 1659
2.18 IPS
 
Image Super-Resolution (F32)
100% 236
8.44 IPS
 
Image Super-Resolution (F16)
100% 236
8.43 IPS
 
Image Super-Resolution (I8)
98% 592
21.2 IPS
 
Text Classification (F32)
100% 218
312.8 IPS
 
Text Classification (F16)
100% 217
311.9 IPS
 
Text Classification (I8)
92% 182
261.3 IPS
 
Machine Translation (F32)
100% 468
8.61 IPS
 
Machine Translation (F16)
100% 480
8.83 IPS
 
Machine Translation (I8)
64% 186
3.42 IPS
 

Compare

Set Baseline Geekbench 6 now available