Geekbench ML Score

420
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date August 17 2024 06:07 PM
Views 1

System Information

System Information
Operating System Android 13
Model LENOVO TB350FU
Model IDLENOVO TB350FU
Motherboard tulip_row_wifi
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 3.73 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 199
37.2 IPS
 
Image Classification (F16)
100% 202
37.7 IPS
 
Image Classification (I8)
97% 347
65.0 IPS
 
Image Segmentation (F32)
100% 301
5.03 IPS
 
Image Segmentation (F16)
100% 308
5.14 IPS
 
Image Segmentation (I8)
98% 420
7.02 IPS
 
Pose Estimation (F32)
100% 417
0.50 IPS
 
Pose Estimation (F16)
100% 404
0.49 IPS
 
Pose Estimation (I8)
100% 1918
2.32 IPS
 
Object Detection (F32)
100% 235
17.5 IPS
 
Object Detection (F16)
100% 234
17.4 IPS
 
Object Detection (I8)
61% 422
31.5 IPS
 
Face Detection (F32)
100% 461
5.48 IPS
 
Face Detection (F16)
100% 457
5.43 IPS
 
Face Detection (I8)
86% 907
10.8 IPS
 
Depth Estimation (F32)
100% 440
3.41 IPS
 
Depth Estimation (F16)
100% 442
3.43 IPS
 
Depth Estimation (I8)
95% 945
7.33 IPS
 
Style Transfer (F32)
100% 672
0.88 IPS
 
Style Transfer (F16)
100% 675
0.89 IPS
 
Style Transfer (I8)
98% 2053
2.70 IPS
 
Image Super-Resolution (F32)
100% 261
9.34 IPS
 
Image Super-Resolution (F16)
100% 257
9.18 IPS
 
Image Super-Resolution (I8)
98% 751
26.8 IPS
 
Text Classification (F32)
100% 250
359.5 IPS
 
Text Classification (F16)
100% 248
357.0 IPS
 
Text Classification (I8)
92% 196
281.5 IPS
 
Machine Translation (F32)
100% 493
9.07 IPS
 
Machine Translation (F16)
100% 493
9.06 IPS
 
Machine Translation (I8)
64% 264
4.86 IPS
 

Compare

Set Baseline Geekbench 6 now available