Geekbench ML Score

222
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for Android AArch64

Result Information

Upload Date September 27 2024 08:52 AM
Views 1

System Information

System Information
Operating System Android 10
Model HUAWEI JNY-LX1
Model IDHUAWEI JNY-LX1
Motherboard JNY
CPU Information
Name vendor
Topology 1 Processor, 8 Cores
Identifier ARM implementer 72 architecture 8 variant 3 part 3392 revision 0
Base Frequency 1.88 GHz
Cluster 16 Cores @ 1.88 GHz
Cluster 22 Cores @ 2.28 GHz
Memory Information
Size 5.56 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 72
7.72 IPS
 
Image Classification (F16)
100% 73
7.79 IPS
 
Image Classification (I8)
81% 158
17.0 IPS
 
Image Segmentation (F32)
100% 344
2.12 IPS
 
Image Segmentation (F16)
100% 336
2.08 IPS
 
Image Segmentation (I8)
89% 564
3.48 IPS
 
Pose Estimation (F32)
100% 138
0.56 IPS
 
Pose Estimation (F16)
100% 140
0.57 IPS
 
Pose Estimation (I8)
80% 140
0.57 IPS
 
Object Detection (F32)
100% 137
4.81 IPS
 
Object Detection (F16)
100% 139
4.87 IPS
 
Object Detection (I8)
52% 300
10.5 IPS
 
Face Detection (F32)
100% 309
3.54 IPS
 
Face Detection (F16)
100% 315
3.62 IPS
 
Face Detection (I8)
75% 352
4.05 IPS
 
Text Classification (F32)
100% 396
156.8 IPS
 
Text Classification (F16)
100% 394
155.6 IPS
 
Machine Translation (F32)
100% 303
46.8 IPS
 
Machine Translation (F16)
100% 303
46.7 IPS
 

Compare

Set Baseline Geekbench 6 now available