Geekbench ML Score

348
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date July 06 2024 07:26 AM
Views 1

System Information

System Information
Operating System Android 13
Model Xiaomi 2201116SG
Model IDXiaomi 2201116SG
Motherboard veux
Governorschedutil
CPU Information
Name ARM ARMv8
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 @ 2.21 GHz
Memory Information
Size 7.26 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 118
22.1 IPS
 
Image Classification (F16)
100% 126
23.5 IPS
 
Image Classification (I8)
97% 374
69.9 IPS
 
Image Segmentation (F32)
100% 250
4.17 IPS
 
Image Segmentation (F16)
100% 238
3.98 IPS
 
Image Segmentation (I8)
98% 419
6.99 IPS
 
Pose Estimation (F32)
100% 296
0.36 IPS
 
Pose Estimation (F16)
100% 267
0.32 IPS
 
Pose Estimation (I8)
100% 1124
1.36 IPS
 
Object Detection (F32)
100% 165
12.4 IPS
 
Object Detection (F16)
100% 177
13.2 IPS
 
Object Detection (I8)
61% 458
34.2 IPS
 
Face Detection (F32)
100% 393
4.67 IPS
 
Face Detection (F16)
100% 385
4.58 IPS
 
Face Detection (I8)
86% 894
10.6 IPS
 
Depth Estimation (F32)
100% 369
2.86 IPS
 
Depth Estimation (F16)
100% 352
2.73 IPS
 
Depth Estimation (I8)
95% 864
6.70 IPS
 
Style Transfer (F32)
100% 600
0.79 IPS
 
Style Transfer (F16)
100% 610
0.80 IPS
 
Style Transfer (I8)
98% 1750
2.30 IPS
 
Image Super-Resolution (F32)
100% 226
8.09 IPS
 
Image Super-Resolution (F16)
100% 224
8.01 IPS
 
Image Super-Resolution (I8)
98% 741
26.5 IPS
 
Text Classification (F32)
100% 201
289.2 IPS
 
Text Classification (F16)
100% 201
289.6 IPS
 
Text Classification (I8)
92% 175
250.9 IPS
 
Machine Translation (F32)
100% 422
7.76 IPS
 
Machine Translation (F16)
100% 400
7.36 IPS
 
Machine Translation (I8)
64% 266
4.90 IPS
 

Compare

Set Baseline Geekbench 6 now available