freescale U4SELF-MX8Q
Geekbench ML Score
26
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.2 for Android AArch64
Result Information
| Upload Date | January 16 2024 12:12 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 10 |
| Model | freescale U4SELF-MX8Q |
| Model ID | freescale U4SELF-MX8Q |
| Motherboard | u4self |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3336 revision 2 |
| Base Frequency | 1.20 GHz |
| Cluster 1 | 4 Cores @ 1.20 GHz |
| Cluster 2 | 2 Cores @ 1.60 GHz |
| Memory Information | |
|---|---|
| Size | 3.61 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
18
1.92 IPS |
|
|
Image Classification (F16)
|
100% |
73
7.83 IPS |
|
|
Image Classification (I8)
|
81% |
157
16.8 IPS |
|
|
Image Segmentation (F32)
|
73% |
82
0.51 IPS |
|
|
Image Segmentation (F16)
|
87% |
3
0.02 IPS |
|
|
Image Segmentation (I8)
|
23% |
137
0.84 IPS |
|
|
Pose Estimation (F32)
|
0
|
||
|
Pose Estimation (F16)
|
0
|
||
|
Pose Estimation (I8)
|
40% |
63
0.25 IPS |
|
|
Object Detection (F32)
|
100% |
109
3.83 IPS |
|
|
Object Detection (F16)
|
0
|
||
|
Object Detection (I8)
|
50% |
374
13.1 IPS |
|
|
Face Detection (F32)
|
100% |
77
0.88 IPS |
|
|
Face Detection (F16)
|
100% |
99
1.13 IPS |
|
|
Face Detection (I8)
|
75% |
132
1.51 IPS |
|
|
Text Classification (F32)
|
100% |
0
0.10 IPS |
|
|
Text Classification (F16)
|
100% |
80
31.7 IPS |
|
|
Machine Translation (F32)
|
100% |
29
4.45 IPS |
|
|
Machine Translation (F16)
|
100% |
22
3.34 IPS |
