rockchip rk3568_r
Geekbench ML Score
61
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | May 14 2022 02:27 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | rockchip rk3568_r |
| Model ID | rockchip rk3568_r |
| Motherboard | rk30sdk |
| Governor | performance |
| CPU Information | |
|---|---|
| Name | ARM Rockchip |
| Topology | 1 Processor, 4 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 2 part 3333 revision 0 |
| Base Frequency | 1.99 GHz |
| Cluster 1 | 4 Cores @ 1.99 GHz |
| Memory Information | |
|---|---|
| Size | 1.91 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
37
4.01 IPS |
|
|
Image Classification (F16)
|
100% |
38
4.05 IPS |
|
|
Image Classification (I8)
|
81% |
117
12.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
96
0.59 IPS |
|
|
Image Segmentation (F16)
|
100% |
86
0.53 IPS |
|
|
Image Segmentation (I8)
|
89% |
191
1.18 IPS |
|
|
Pose Estimation (F32)
|
100% |
27
0.11 IPS |
|
|
Pose Estimation (F16)
|
100% |
31
0.12 IPS |
|
|
Pose Estimation (I8)
|
80% |
48
0.19 IPS |
|
|
Object Detection (F32)
|
100% |
63
2.22 IPS |
|
|
Object Detection (F16)
|
100% |
63
2.23 IPS |
|
|
Object Detection (I8)
|
52% |
134
4.72 IPS |
|
|
Face Detection (F32)
|
100% |
80
0.91 IPS |
|
|
Face Detection (F16)
|
100% |
86
0.99 IPS |
|
|
Face Detection (I8)
|
75% |
188
2.16 IPS |
|
|
Text Classification (F32)
|
100% |
81
32.1 IPS |
|
|
Text Classification (F16)
|
100% |
82
32.3 IPS |
|
|
Machine Translation (F32)
|
100% |
14
2.17 IPS |
|
|
Machine Translation (F16)
|
100% |
15
2.23 IPS |
