Khadas rk3588_s
Geekbench ML Score
157
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | August 06 2022 05:28 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | Khadas rk3588_s |
| Model ID | Khadas rk3588_s |
| Motherboard | rk30sdk |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 4 Cores @ 1.80 GHz |
| Cluster 2 | 2 Cores @ 2.26 GHz |
| Cluster 3 | 2 Cores @ 2.30 GHz |
| Memory Information | |
|---|---|
| Size | 7.49 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
47
5.04 IPS |
|
|
Image Classification (F16)
|
100% |
47
5.02 IPS |
|
|
Image Classification (I8)
|
81% |
157
16.8 IPS |
|
|
Image Segmentation (F32)
|
100% |
182
1.13 IPS |
|
|
Image Segmentation (F16)
|
100% |
175
1.08 IPS |
|
|
Image Segmentation (I8)
|
89% |
564
3.48 IPS |
|
|
Pose Estimation (F32)
|
100% |
138
0.56 IPS |
|
|
Pose Estimation (F16)
|
100% |
103
0.42 IPS |
|
|
Pose Estimation (I8)
|
80% |
127
0.51 IPS |
|
|
Object Detection (F32)
|
100% |
78
2.74 IPS |
|
|
Object Detection (F16)
|
100% |
75
2.64 IPS |
|
|
Object Detection (I8)
|
52% |
265
9.28 IPS |
|
|
Face Detection (F32)
|
100% |
184
2.11 IPS |
|
|
Face Detection (F16)
|
100% |
163
1.87 IPS |
|
|
Face Detection (I8)
|
75% |
350
4.02 IPS |
|
|
Text Classification (F32)
|
100% |
291
115.0 IPS |
|
|
Text Classification (F16)
|
100% |
452
178.8 IPS |
|
|
Machine Translation (F32)
|
100% |
157
24.1 IPS |
|
|
Machine Translation (F16)
|
100% |
154
23.7 IPS |
