FCNT F-51B
Geekbench ML Score
202
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | March 02 2023 01:11 PM |
| Views | 19 |
System Information
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | FCNT F-51B |
| Model ID | FCNT F-51B |
| Motherboard | F51B |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | Qualcomm ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 81 architecture 8 variant 8 part 2052 revision 14 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 6 Cores @ 1.80 GHz |
| Cluster 2 | 2 Cores @ 2.04 GHz |
| Memory Information | |
|---|---|
| Size | 3.38 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
94
10.1 IPS |
|
|
Image Classification (F16)
|
100% |
91
9.75 IPS |
|
|
Image Classification (I8)
|
81% |
235
25.2 IPS |
|
|
Image Segmentation (F32)
|
100% |
298
1.84 IPS |
|
|
Image Segmentation (F16)
|
100% |
270
1.67 IPS |
|
|
Image Segmentation (I8)
|
89% |
550
3.39 IPS |
|
|
Pose Estimation (F32)
|
100% |
137
0.55 IPS |
|
|
Pose Estimation (F16)
|
100% |
137
0.55 IPS |
|
|
Pose Estimation (I8)
|
80% |
142
0.58 IPS |
|
|
Object Detection (F32)
|
100% |
132
4.63 IPS |
|
|
Object Detection (F16)
|
100% |
132
4.63 IPS |
|
|
Object Detection (I8)
|
52% |
247
8.67 IPS |
|
|
Face Detection (F32)
|
100% |
250
2.87 IPS |
|
|
Face Detection (F16)
|
100% |
247
2.84 IPS |
|
|
Face Detection (I8)
|
75% |
429
4.93 IPS |
|
|
Text Classification (F32)
|
100% |
214
84.6 IPS |
|
|
Text Classification (F16)
|
100% |
221
87.4 IPS |
|
|
Machine Translation (F32)
|
100% |
225
34.7 IPS |
|
|
Machine Translation (F16)
|
100% |
226
34.8 IPS |
