Geekbench ML Score

139
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date December 06 2024 12:02 AM
Views 1

System Information

System Information
Operating System Android 13
Model INFINIX Infinix X6528B
Model IDINFINIX Infinix X6528B
Motherboard Infinix-X6528B
Governorschedutil
CPU Information
Name ARM Unisoc
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3338 revision 1
Base Frequency 1.61 GHz
Cluster 18 Cores @ 1.61 GHz
Memory Information
Size 7.59 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 80
15.0 IPS
 
Image Classification (F16)
100% 79
14.9 IPS
 
Image Classification (I8)
99% 107
20.1 IPS
 
Image Segmentation (F32)
100% 99
1.65 IPS
 
Image Segmentation (F16)
100% 98
1.64 IPS
 
Image Segmentation (I8)
98% 136
2.27 IPS
 
Pose Estimation (F32)
100% 449
0.54 IPS
 
Pose Estimation (F16)
100% 448
0.54 IPS
 
Pose Estimation (I8)
100% 415
0.50 IPS
 
Object Detection (F32)
100% 43
3.24 IPS
 
Object Detection (F16)
100% 43
3.24 IPS
 
Object Detection (I8)
61% 82
6.10 IPS
 
Face Detection (F32)
100% 263
3.13 IPS
 
Face Detection (F16)
100% 262
3.11 IPS
 
Face Detection (I8)
86% 204
2.43 IPS
 
Depth Estimation (F32)
100% 364
2.82 IPS
 
Depth Estimation (F16)
100% 365
2.83 IPS
 
Depth Estimation (I8)
96% 391
3.03 IPS
 
Style Transfer (F32)
100% 323
0.43 IPS
 
Style Transfer (F16)
100% 326
0.43 IPS
 
Style Transfer (I8)
97% 548
0.72 IPS
 
Image Super-Resolution (F32)
100% 207
7.39 IPS
 
Image Super-Resolution (F16)
100% 207
7.41 IPS
 
Image Super-Resolution (I8)
98% 221
7.90 IPS
 
Text Classification (F32)
100% 20
28.6 IPS
 
Text Classification (F16)
100% 20
28.7 IPS
 
Text Classification (I8)
94% 25
36.6 IPS
 
Machine Translation (F32)
100% 72
1.33 IPS
 
Machine Translation (F16)
100% 103
1.90 IPS
 
Machine Translation (I8)
57% 71
1.31 IPS
 

Compare

Set Baseline Geekbench 6 now available