UNISOC ums512_25c10_Natv
Geekbench ML Score
178
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | October 21 2021 07:05 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | UNISOC ums512_25c10_Natv |
| Model ID | UNISOC ums512_25c10_Natv |
| Motherboard | ums512_25c10 |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM Unisoc |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
| Base Frequency | 2.00 GHz |
| Cluster 1 | 8 Cores @ 2.00 GHz |
| Memory Information | |
|---|---|
| Size | 2.43 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
118
12.7 IPS |
|
|
Image Classification (F16)
|
100% |
117
12.5 IPS |
|
|
Image Classification (I8)
|
81% |
224
24.0 IPS |
|
|
Image Segmentation (F32)
|
100% |
242
1.50 IPS |
|
|
Image Segmentation (F16)
|
100% |
244
1.51 IPS |
|
|
Image Segmentation (I8)
|
89% |
549
3.39 IPS |
|
|
Pose Estimation (F32)
|
100% |
95
0.39 IPS |
|
|
Pose Estimation (F16)
|
100% |
84
0.34 IPS |
|
|
Pose Estimation (I8)
|
80% |
132
0.53 IPS |
|
|
Object Detection (F32)
|
100% |
164
5.76 IPS |
|
|
Object Detection (F16)
|
100% |
166
5.83 IPS |
|
|
Object Detection (I8)
|
52% |
272
9.53 IPS |
|
|
Face Detection (F32)
|
100% |
228
2.62 IPS |
|
|
Face Detection (F16)
|
100% |
222
2.55 IPS |
|
|
Face Detection (I8)
|
75% |
395
4.53 IPS |
|
|
Text Classification (F32)
|
100% |
152
60.1 IPS |
|
|
Text Classification (F16)
|
100% |
157
62.2 IPS |
|
|
Machine Translation (F32)
|
100% |
127
19.6 IPS |
|
|
Machine Translation (F16)
|
100% |
127
19.6 IPS |
