Raspberry Raspberry Pi 4
Geekbench ML Score
89
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| User | GyBHard |
| Upload Date | January 20 2022 05:31 AM |
| Views | 5 |
System Information
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | Raspberry Raspberry Pi 4 |
| Model ID | Raspberry Raspberry Pi 4 |
| Motherboard | |
| Governor | performance |
| CPU Information | |
|---|---|
| Name | ARM BCM2835 |
| Topology | 1 Processor, 4 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3336 revision 3 |
| Base Frequency | 1.50 GHz |
| Cluster 1 | 4 Cores @ 1.50 GHz |
| Memory Information | |
|---|---|
| Size | 3.70 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
78
8.36 IPS |
|
|
Image Classification (F16)
|
100% |
78
8.37 IPS |
|
|
Image Classification (I8)
|
81% |
87
9.37 IPS |
|
|
Image Segmentation (F32)
|
100% |
135
0.83 IPS |
|
|
Image Segmentation (F16)
|
100% |
135
0.83 IPS |
|
|
Image Segmentation (I8)
|
89% |
157
0.97 IPS |
|
|
Pose Estimation (F32)
|
100% |
53
0.21 IPS |
|
|
Pose Estimation (F16)
|
100% |
53
0.22 IPS |
|
|
Pose Estimation (I8)
|
80% |
27
0.11 IPS |
|
|
Object Detection (F32)
|
100% |
100
3.49 IPS |
|
|
Object Detection (F16)
|
100% |
100
3.49 IPS |
|
|
Object Detection (I8)
|
52% |
108
3.78 IPS |
|
|
Face Detection (F32)
|
100% |
105
1.21 IPS |
|
|
Face Detection (F16)
|
100% |
107
1.23 IPS |
|
|
Face Detection (I8)
|
75% |
117
1.34 IPS |
|
|
Text Classification (F32)
|
100% |
132
52.3 IPS |
|
|
Text Classification (F16)
|
100% |
132
52.2 IPS |
|
|
Machine Translation (F32)
|
100% |
69
10.6 IPS |
|
|
Machine Translation (F16)
|
100% |
68
10.5 IPS |
