Geekbench ML Score

449
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date May 03 2024 04:05 PM
Views 1

System Information

System Information
Operating System Android 14
Model vivo V2319
Model IDvivo V2319
Motherboard k6895v1_64
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 14 Cores @ 2.00 GHz
Cluster 23 Cores @ 3.00 GHz
Cluster 31 Core @ 3.10 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% 214
40.1 IPS
 
Image Classification (F16)
100% 230
43.1 IPS
 
Image Classification (I8)
97% 316
59.1 IPS
 
Image Segmentation (F32)
100% 292
4.88 IPS
 
Image Segmentation (F16)
100% 302
5.05 IPS
 
Image Segmentation (I8)
98% 447
7.46 IPS
 
Pose Estimation (F32)
100% 507
0.61 IPS
 
Pose Estimation (F16)
100% 520
0.63 IPS
 
Pose Estimation (I8)
100% 1759
2.13 IPS
 
Object Detection (F32)
100% 228
17.0 IPS
 
Object Detection (F16)
100% 206
15.4 IPS
 
Object Detection (I8)
61% 443
33.1 IPS
 
Face Detection (F32)
100% 432
5.14 IPS
 
Face Detection (F16)
100% 452
5.38 IPS
 
Face Detection (I8)
86% 820
9.75 IPS
 
Depth Estimation (F32)
100% 472
3.66 IPS
 
Depth Estimation (F16)
100% 500
3.88 IPS
 
Depth Estimation (I8)
95% 799
6.20 IPS
 
Style Transfer (F32)
100% 1057
1.39 IPS
 
Style Transfer (F16)
100% 1095
1.44 IPS
 
Style Transfer (I8)
98% 2212
2.91 IPS
 
Image Super-Resolution (F32)
100% 291
10.4 IPS
 
Image Super-Resolution (F16)
100% 310
11.1 IPS
 
Image Super-Resolution (I8)
98% 958
34.2 IPS
 
Text Classification (F32)
100% 333
478.7 IPS
 
Text Classification (F16)
100% 324
466.3 IPS
 
Text Classification (I8)
92% 258
371.1 IPS
 
Machine Translation (F32)
100% 407
7.50 IPS
 
Machine Translation (F16)
100% 404
7.43 IPS
 
Machine Translation (I8)
64% 211
3.87 IPS
 

Compare

Set Baseline Geekbench 6 now available