brcm Raspberry Pi 4
Geekbench ML Score
44
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | October 28 2022 02:41 AM |
| Views | 7 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | brcm Raspberry Pi 4 |
| Model ID | brcm Raspberry Pi 4 |
| Motherboard | |
| Governor | powersave |
| 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 | 3.69 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
42
4.53 IPS |
|
|
Image Classification (F16)
|
100% |
43
4.57 IPS |
|
|
Image Classification (I8)
|
81% |
36
3.86 IPS |
|
|
Image Segmentation (F32)
|
100% |
64
0.39 IPS |
|
|
Image Segmentation (F16)
|
100% |
63
0.39 IPS |
|
|
Image Segmentation (I8)
|
89% |
64
0.40 IPS |
|
|
Pose Estimation (F32)
|
100% |
26
0.10 IPS |
|
|
Pose Estimation (F16)
|
100% |
26
0.10 IPS |
|
|
Pose Estimation (I8)
|
80% |
11
0.05 IPS |
|
|
Object Detection (F32)
|
100% |
51
1.79 IPS |
|
|
Object Detection (F16)
|
100% |
51
1.79 IPS |
|
|
Object Detection (I8)
|
52% |
44
1.55 IPS |
|
|
Face Detection (F32)
|
100% |
62
0.71 IPS |
|
|
Face Detection (F16)
|
100% |
62
0.71 IPS |
|
|
Face Detection (I8)
|
75% |
49
0.56 IPS |
|
|
Text Classification (F32)
|
100% |
57
22.7 IPS |
|
|
Text Classification (F16)
|
100% |
57
22.7 IPS |
|
|
Machine Translation (F32)
|
100% |
46
7.02 IPS |
|
|
Machine Translation (F16)
|
100% |
45
6.95 IPS |
