Geekbench ML Score

406
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date July 17 2024 06:05 PM
Views 1

System Information

System Information
Operating System Android 14
Model OPPO CPH2643
Model IDOPPO CPH2643
Motherboard k6877v1_64_k419
CPU Information
Name ARM MT6877V/TTZA
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.60 GHz
Memory Information
Size 7.35 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 150
28.1 IPS
 
Image Classification (F16)
100% 178
33.3 IPS
 
Image Classification (I8)
97% 387
72.4 IPS
 
Image Segmentation (F32)
100% 211
3.52 IPS
 
Image Segmentation (F16)
100% 263
4.39 IPS
 
Image Segmentation (I8)
98% 460
7.68 IPS
 
Pose Estimation (F32)
100% 417
0.50 IPS
 
Pose Estimation (F16)
100% 415
0.50 IPS
 
Pose Estimation (I8)
100% 1712
2.07 IPS
 
Object Detection (F32)
100% 210
15.7 IPS
 
Object Detection (F16)
100% 202
15.1 IPS
 
Object Detection (I8)
61% 466
34.8 IPS
 
Face Detection (F32)
100% 446
5.30 IPS
 
Face Detection (F16)
100% 443
5.26 IPS
 
Face Detection (I8)
86% 950
11.3 IPS
 
Depth Estimation (F32)
100% 444
3.44 IPS
 
Depth Estimation (F16)
100% 461
3.57 IPS
 
Depth Estimation (I8)
95% 970
7.52 IPS
 
Style Transfer (F32)
100% 755
0.99 IPS
 
Style Transfer (F16)
100% 750
0.99 IPS
 
Style Transfer (I8)
98% 1971
2.59 IPS
 
Image Super-Resolution (F32)
100% 248
8.85 IPS
 
Image Super-Resolution (F16)
100% 249
8.90 IPS
 
Image Super-Resolution (I8)
98% 682
24.3 IPS
 
Text Classification (F32)
100% 256
367.5 IPS
 
Text Classification (F16)
100% 202
289.9 IPS
 
Text Classification (I8)
92% 215
309.4 IPS
 
Machine Translation (F32)
100% 448
8.24 IPS
 
Machine Translation (F16)
100% 471
8.66 IPS
 
Machine Translation (I8)
64% 297
5.46 IPS
 

Compare

Set Baseline Geekbench 6 now available