Raspberry Raspberry Pi 4
Geekbench ML Score
118
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | December 07 2022 05:20 AM |
| Views | 15 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| 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 | 3.69 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
75
8.07 IPS |
|
|
Image Classification (F16)
|
100% |
74
7.94 IPS |
|
|
Image Classification (I8)
|
81% |
262
28.0 IPS |
|
|
Image Segmentation (F32)
|
100% |
138
0.85 IPS |
|
|
Image Segmentation (F16)
|
100% |
136
0.84 IPS |
|
|
Image Segmentation (I8)
|
89% |
466
2.88 IPS |
|
|
Pose Estimation (F32)
|
100% |
51
0.21 IPS |
|
|
Pose Estimation (F16)
|
100% |
51
0.21 IPS |
|
|
Pose Estimation (I8)
|
80% |
99
0.40 IPS |
|
|
Object Detection (F32)
|
100% |
100
3.50 IPS |
|
|
Object Detection (F16)
|
100% |
99
3.49 IPS |
|
|
Object Detection (I8)
|
52% |
245
8.59 IPS |
|
|
Face Detection (F32)
|
100% |
108
1.25 IPS |
|
|
Face Detection (F16)
|
100% |
110
1.26 IPS |
|
|
Face Detection (I8)
|
75% |
339
3.90 IPS |
|
|
Text Classification (F32)
|
100% |
127
50.2 IPS |
|
|
Text Classification (F16)
|
100% |
128
50.5 IPS |
|
|
Machine Translation (F32)
|
100% |
68
10.4 IPS |
|
|
Machine Translation (F16)
|
100% |
68
10.5 IPS |
