Raspberry Raspberry Pi 4
Geekbench ML Score
74
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | August 14 2021 08:27 PM |
| Views | 8 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | Raspberry Raspberry Pi 4 |
| Model ID | Raspberry Raspberry Pi 4 |
| Motherboard | |
| Governor | ondemand |
| CPU Information | |
|---|---|
| Name | ARM BCM2835 |
| Topology | 1 Processor, 4 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3336 revision 3 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 4 Cores @ 1.80 GHz |
| Memory Information | |
|---|---|
| Size | 3.70 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
42
4.50 IPS |
|
|
Image Classification (F16)
|
100% |
42
4.48 IPS |
|
|
Image Classification (I8)
|
81% |
116
12.4 IPS |
|
|
Image Segmentation (F32)
|
100% |
79
0.49 IPS |
|
|
Image Segmentation (F16)
|
100% |
79
0.49 IPS |
|
|
Image Segmentation (I8)
|
89% |
211
1.30 IPS |
|
|
Pose Estimation (F32)
|
100% |
26
0.10 IPS |
|
|
Pose Estimation (F16)
|
100% |
25
0.10 IPS |
|
|
Pose Estimation (I8)
|
80% |
69
0.28 IPS |
|
|
Object Detection (F32)
|
100% |
55
1.93 IPS |
|
|
Object Detection (F16)
|
100% |
57
1.98 IPS |
|
|
Object Detection (I8)
|
52% |
110
3.86 IPS |
|
|
Face Detection (F32)
|
100% |
69
0.79 IPS |
|
|
Face Detection (F16)
|
100% |
70
0.80 IPS |
|
|
Face Detection (I8)
|
75% |
160
1.83 IPS |
|
|
Text Classification (F32)
|
100% |
151
59.8 IPS |
|
|
Text Classification (F16)
|
100% |
149
58.9 IPS |
|
|
Machine Translation (F32)
|
100% |
74
11.4 IPS |
|
|
Machine Translation (F16)
|
100% |
73
11.3 IPS |
