[2019] Tablet: Dragon Touch Max10 [S5V-TABK10] incar MAX 10
Geekbench ML Score
32
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for Android AArch64
Result Information
| User | inc7007 |
| Upload Date | August 17 2024 04:04 PM |
| Views | 3 |
System Information
| System Information | |
|---|---|
| Operating System | Android 9 |
| Model | incar MAX 10 |
| Model ID | incar MAX 10 |
| Motherboard | sp9863a_2h10 |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM Unisoc |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3333 revision 0 |
| Base Frequency | 1.20 GHz |
| Cluster 1 | 4 Cores @ 1.20 GHz |
| Cluster 2 | 4 Cores @ 1.60 GHz |
| Memory Information | |
|---|---|
| Size | 2.76 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
26
2.80 IPS |
|
|
Image Classification (F16)
|
100% |
37
4.00 IPS |
|
|
Image Classification (I8)
|
80% |
37
3.94 IPS |
|
|
Image Segmentation (F32)
|
100% |
89
0.55 IPS |
|
|
Image Segmentation (F16)
|
100% |
89
0.55 IPS |
|
|
Image Segmentation (I8)
|
89% |
82
0.50 IPS |
|
|
Pose Estimation (F32)
|
100% |
4
0.02 IPS |
|
|
Pose Estimation (F16)
|
100% |
4
0.02 IPS |
|
|
Pose Estimation (I8)
|
80% |
4
0.02 IPS |
|
|
Object Detection (F32)
|
100% |
29
1.02 IPS |
|
|
Object Detection (F16)
|
100% |
41
1.42 IPS |
|
|
Object Detection (I8)
|
54% |
40
1.42 IPS |
|
|
Face Detection (F32)
|
100% |
99
1.13 IPS |
|
|
Face Detection (F16)
|
100% |
99
1.13 IPS |
|
|
Face Detection (I8)
|
75% |
49
0.57 IPS |
|
|
Text Classification (F32)
|
100% |
85
33.5 IPS |
|
|
Text Classification (F16)
|
100% |
85
33.4 IPS |
|
|
Machine Translation (F32)
|
100% |
17
2.67 IPS |
|
|
Machine Translation (F16)
|
100% |
17
2.68 IPS |
