Geekbench ML Score

370
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date July 27 2024 06:04 AM
Views 1

System Information

System Information
Operating System Android 14
Model vivo V2231
Model IDvivo V2231
Motherboard k6886v1_64
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3405 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.80 GHz
Memory Information
Size 7.25 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 179
33.6 IPS
 
Image Classification (F16)
100% 203
38.0 IPS
 
Image Classification (I8)
97% 255
47.8 IPS
 
Image Segmentation (F32)
100% 263
4.40 IPS
 
Image Segmentation (F16)
100% 254
4.23 IPS
 
Image Segmentation (I8)
98% 429
7.16 IPS
 
Pose Estimation (F32)
100% 397
0.48 IPS
 
Pose Estimation (F16)
100% 379
0.46 IPS
 
Pose Estimation (I8)
100% 1585
1.92 IPS
 
Object Detection (F32)
100% 186
13.9 IPS
 
Object Detection (F16)
100% 182
13.6 IPS
 
Object Detection (I8)
61% 356
26.6 IPS
 
Face Detection (F32)
100% 413
4.91 IPS
 
Face Detection (F16)
100% 400
4.75 IPS
 
Face Detection (I8)
86% 749
8.90 IPS
 
Depth Estimation (F32)
100% 438
3.40 IPS
 
Depth Estimation (F16)
100% 391
3.03 IPS
 
Depth Estimation (I8)
95% 863
6.69 IPS
 
Style Transfer (F32)
100% 810
1.07 IPS
 
Style Transfer (F16)
100% 775
1.02 IPS
 
Style Transfer (I8)
98% 2249
2.96 IPS
 
Image Super-Resolution (F32)
100% 251
8.98 IPS
 
Image Super-Resolution (F16)
100% 231
8.26 IPS
 
Image Super-Resolution (I8)
98% 696
24.8 IPS
 
Text Classification (F32)
100% 207
297.6 IPS
 
Text Classification (F16)
100% 211
303.6 IPS
 
Text Classification (I8)
92% 194
279.3 IPS
 
Machine Translation (F32)
100% 266
4.89 IPS
 
Machine Translation (F16)
100% 260
4.79 IPS
 
Machine Translation (I8)
64% 247
4.55 IPS
 

Compare

Set Baseline Geekbench 6 now available