Geekbench ML Score

202
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 14 2023 10:19 AM
Views 1

System Information

System Information
Operating System Android 9
Model Asus Zenfone Max Pro (M1)
Model IDasus ASUS_X00TD
Motherboard sdm660
Governorinteractive
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 10 part 2048 revision 2
Base Frequency 1.61 GHz
Cluster 14 Cores @ 1.61 GHz
Cluster 24 Cores @ 1.80 GHz
Memory Information
Size 2.68 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 112
12.0 IPS
 
Image Classification (F16)
100% 243
26.0 IPS
 
Image Classification (I8)
80% 261
28.0 IPS
 
Image Segmentation (F32)
100% 234
1.45 IPS
 
Image Segmentation (F16)
100% 513
3.17 IPS
 
Image Segmentation (I8)
89% 588
3.63 IPS
 
Pose Estimation (F32)
100% 107
0.43 IPS
 
Pose Estimation (F16)
100% 246
0.99 IPS
 
Pose Estimation (I8)
80% 243
0.98 IPS
 
Object Detection (F32)
100% 96
3.36 IPS
 
Object Detection (F16)
99% 151
5.29 IPS
 
Object Detection (I8)
53% 160
5.63 IPS
 
Face Detection (F32)
100% 240
2.76 IPS
 
Face Detection (F16)
97% 496
5.70 IPS
 
Face Detection (I8)
75% 461
5.30 IPS
 
Text Classification (F32)
100% 128
50.6 IPS
 
Text Classification (F16)
98% 212
84.0 IPS
 
Machine Translation (F32)
100% 79
12.1 IPS
 
Machine Translation (F16)
100% 78
12.0 IPS
 

Compare

Set Baseline Geekbench 6 now available