Geekbench ML Score

408
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date May 29 2024 08:38 AM
Views 1

System Information

System Information
Operating System Android 13
Model motorola moto g54 5G
Model IDmotorola moto g54 5G
Motherboard cancunf
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.20 GHz
Memory Information
Size 11.35 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 186
34.9 IPS
 
Image Classification (F16)
100% 190
35.5 IPS
 
Image Classification (I8)
97% 391
73.2 IPS
 
Image Segmentation (F32)
100% 266
4.45 IPS
 
Image Segmentation (F16)
100% 278
4.64 IPS
 
Image Segmentation (I8)
98% 457
7.63 IPS
 
Pose Estimation (F32)
100% 386
0.47 IPS
 
Pose Estimation (F16)
100% 384
0.46 IPS
 
Pose Estimation (I8)
100% 1779
2.15 IPS
 
Object Detection (F32)
100% 206
15.4 IPS
 
Object Detection (F16)
100% 206
15.3 IPS
 
Object Detection (I8)
61% 438
32.7 IPS
 
Face Detection (F32)
100% 445
5.30 IPS
 
Face Detection (F16)
100% 442
5.25 IPS
 
Face Detection (I8)
86% 963
11.4 IPS
 
Depth Estimation (F32)
100% 426
3.30 IPS
 
Depth Estimation (F16)
100% 418
3.24 IPS
 
Depth Estimation (I8)
95% 1011
7.84 IPS
 
Style Transfer (F32)
100% 731
0.96 IPS
 
Style Transfer (F16)
100% 730
0.96 IPS
 
Style Transfer (I8)
98% 2086
2.74 IPS
 
Image Super-Resolution (F32)
100% 256
9.13 IPS
 
Image Super-Resolution (F16)
100% 249
8.88 IPS
 
Image Super-Resolution (I8)
98% 681
24.3 IPS
 
Text Classification (F32)
100% 225
322.7 IPS
 
Text Classification (F16)
100% 222
318.8 IPS
 
Text Classification (I8)
92% 189
271.2 IPS
 
Machine Translation (F32)
100% 480
8.84 IPS
 
Machine Translation (F16)
100% 487
8.96 IPS
 
Machine Translation (I8)
64% 260
4.78 IPS
 

Compare

Set Baseline Geekbench 6 now available