Upload Date | August 19 2024 09:44 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 12 |
Model | rockchip orangepi5b |
Model ID | rockchip orangepi5b |
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 | 4 Cores @ 2.26 GHz |
Memory Information | |
---|---|
Size | 15.57 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
484
51.8 IPS |
|
Image Classification (F16)
|
100% |
728
78.0 IPS |
|
Image Classification (I8)
|
81% |
670
71.8 IPS |
|
Image Segmentation (F32)
|
100% |
949
5.86 IPS |
|
Image Segmentation (F16)
|
100% |
1742
10.8 IPS |
|
Image Segmentation (I8)
|
89% |
1758
10.9 IPS |
|
Pose Estimation (F32)
|
100% |
463
1.87 IPS |
|
Pose Estimation (F16)
|
100% |
916
3.71 IPS |
|
Pose Estimation (I8)
|
80% |
929
3.76 IPS |
|
Object Detection (F32)
|
100% |
541
19.0 IPS |
|
Object Detection (F16)
|
99% |
712
25.0 IPS |
|
Object Detection (I8)
|
54% |
688
24.1 IPS |
|
Face Detection (F32)
|
100% |
1119
12.9 IPS |
|
Face Detection (F16)
|
97% |
1800
20.7 IPS |
|
Face Detection (I8)
|
75% |
1689
19.4 IPS |
|
Text Classification (F32)
|
100% |
625
247.2 IPS |
|
Text Classification (F16)
|
98% |
937
370.6 IPS |
|
Machine Translation (F32)
|
100% |
300
46.2 IPS |
|
Machine Translation (F16)
|
100% |
279
43.0 IPS |