Geekbench ML Score

171
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date May 26 2024 05:27 PM
Views 1

System Information

System Information
Operating System Android 13
Model FOSSiBOT F102
Model IDFOSSiBOT F102
Motherboard k6789v1_64
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.20 GHz
Memory Information
Size 11.52 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 94
17.5 IPS
 
Image Classification (F16)
100% 163
30.5 IPS
 
Image Classification (I8)
97% 154
28.9 IPS
 
Image Segmentation (F32)
100% 104
1.74 IPS
 
Image Segmentation (F16)
100% 181
3.02 IPS
 
Image Segmentation (I8)
98% 230
3.85 IPS
 
Pose Estimation (F32)
100% 89
0.11 IPS
 
Pose Estimation (F16)
100% 104
0.13 IPS
 
Pose Estimation (I8)
100% 104
0.13 IPS
 
Object Detection (F32)
100% 59
4.42 IPS
 
Object Detection (F16)
100% 100
7.50 IPS
 
Object Detection (I8)
62% 88
6.56 IPS
 
Face Detection (F32)
100% 217
2.59 IPS
 
Face Detection (F16)
98% 316
3.76 IPS
 
Face Detection (I8)
86% 313
3.72 IPS
 
Depth Estimation (F32)
100% 171
1.33 IPS
 
Depth Estimation (F16)
100% 220
1.70 IPS
 
Depth Estimation (I8)
95% 220
1.70 IPS
 
Style Transfer (F32)
100% 339
0.45 IPS
 
Style Transfer (F16)
100% 477
0.63 IPS
 
Style Transfer (I8)
98% 476
0.63 IPS
 
Image Super-Resolution (F32)
100% 93
3.33 IPS
 
Image Super-Resolution (F16)
100% 137
4.88 IPS
 
Image Super-Resolution (I8)
98% 142
5.07 IPS
 
Text Classification (F32)
100% 145
208.3 IPS
 
Text Classification (F16)
100% 145
208.0 IPS
 
Text Classification (I8)
92% 235
337.5 IPS
 
Machine Translation (F32)
100% 267
4.92 IPS
 
Machine Translation (F16)
100% 266
4.90 IPS
 
Machine Translation (I8)
64% 242
4.44 IPS
 

Compare

Set Baseline Geekbench 6 now available