Unihertz Atom
Geekbench ML Score
73
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for Android AArch64
Result Information
| Upload Date | August 25 2024 02:58 PM |
| Views | 3 |
System Information
| System Information | |
|---|---|
| Operating System | Android 9 |
| Model | Unihertz Atom |
| Model ID | Unihertz Atom |
| Motherboard | g35v63c2k_dfl |
| Governor | interactive |
| CPU Information | |
|---|---|
| Name | ARM MT6763V/B |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3331 revision 4 |
| Base Frequency | 1.51 GHz |
| Cluster 1 | 4 Cores @ 1.51 GHz |
| Cluster 2 | 4 Cores @ 2.00 GHz |
| Memory Information | |
|---|---|
| Size | 3.74 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
48
5.19 IPS |
|
|
Image Classification (F16)
|
100% |
52
5.58 IPS |
|
|
Image Classification (I8)
|
81% |
152
16.3 IPS |
|
|
Image Segmentation (F32)
|
100% |
92
0.57 IPS |
|
|
Image Segmentation (F16)
|
100% |
91
0.56 IPS |
|
|
Image Segmentation (I8)
|
89% |
360
2.22 IPS |
|
|
Pose Estimation (F32)
|
100% |
40
0.16 IPS |
|
|
Pose Estimation (F16)
|
100% |
37
0.15 IPS |
|
|
Pose Estimation (I8)
|
80% |
74
0.30 IPS |
|
|
Object Detection (F32)
|
100% |
92
3.21 IPS |
|
|
Object Detection (F16)
|
100% |
94
3.30 IPS |
|
|
Object Detection (I8)
|
52% |
266
9.33 IPS |
|
|
Face Detection (F32)
|
100% |
102
1.18 IPS |
|
|
Face Detection (F16)
|
100% |
99
1.14 IPS |
|
|
Face Detection (I8)
|
75% |
244
2.80 IPS |
|
|
Text Classification (F32)
|
100% |
56
22.0 IPS |
|
|
Text Classification (F16)
|
100% |
56
22.0 IPS |
|
|
Machine Translation (F32)
|
100% |
12
1.92 IPS |
|
|
Machine Translation (F16)
|
100% |
12
1.89 IPS |
