Geekbench ML Score

175
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date May 18 2024 08:49 AM
Views 1

System Information

System Information
Operating System Android 14
Model Samsung Galaxy A53 5G
Model IDsamsung SM-A536E
Motherboard s5e8825
Governorenergy_aware
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.40 GHz
Memory Information
Size 5.26 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 26
4.93 IPS
 
Image Classification (F16)
100% 41
7.74 IPS
 
Image Classification (I8)
97% 85
15.9 IPS
 
Image Segmentation (F32)
100% 145
2.42 IPS
 
Image Segmentation (F16)
100% 154
2.57 IPS
 
Image Segmentation (I8)
98% 276
4.61 IPS
 
Pose Estimation (F32)
100% 351
0.42 IPS
 
Pose Estimation (F16)
100% 356
0.43 IPS
 
Pose Estimation (I8)
100% 1902
2.30 IPS
 
Object Detection (F32)
100% 71
5.29 IPS
 
Object Detection (F16)
100% 76
5.66 IPS
 
Object Detection (I8)
61% 162
12.1 IPS
 
Face Detection (F32)
100% 200
2.38 IPS
 
Face Detection (F16)
100% 192
2.28 IPS
 
Face Detection (I8)
86% 355
4.22 IPS
 
Depth Estimation (F32)
100% 234
1.81 IPS
 
Depth Estimation (F16)
100% 229
1.78 IPS
 
Depth Estimation (I8)
95% 487
3.78 IPS
 
Style Transfer (F32)
100% 637
0.84 IPS
 
Style Transfer (F16)
100% 633
0.83 IPS
 
Style Transfer (I8)
98% 1417
1.86 IPS
 
Image Super-Resolution (F32)
100% 112
3.99 IPS
 
Image Super-Resolution (F16)
100% 112
3.99 IPS
 
Image Super-Resolution (I8)
98% 479
17.1 IPS
 
Text Classification (F32)
100% 60
86.3 IPS
 
Text Classification (F16)
100% 54
77.7 IPS
 
Text Classification (I8)
92% 46
66.0 IPS
 
Machine Translation (F32)
100% 104
1.92 IPS
 
Machine Translation (F16)
100% 108
1.99 IPS
 
Machine Translation (I8)
64% 93
1.71 IPS
 

Compare

Set Baseline Geekbench 6 now available