Sony XQ-BT52
Geekbench ML Score
449
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| User | Puffin |
| Upload Date | August 08 2021 11:14 PM |
| Views | 7 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | Sony XQ-BT52 |
| Model ID | Sony XQ-BT52 |
| Motherboard | lito |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 revision 0 |
| Base Frequency | 1.71 GHz |
| Cluster 1 | 6 Cores @ 1.71 GHz |
| Cluster 2 | 2 Cores @ 2.07 GHz |
| Memory Information | |
|---|---|
| Size | 5.35 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
328
35.1 IPS |
|
|
Image Classification (F16)
|
100% |
472
50.6 IPS |
|
|
Image Classification (I8)
|
80% |
434
46.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
739
4.56 IPS |
|
|
Image Segmentation (F16)
|
100% |
1117
6.90 IPS |
|
|
Image Segmentation (I8)
|
89% |
1036
6.40 IPS |
|
|
Pose Estimation (F32)
|
100% |
369
1.49 IPS |
|
|
Pose Estimation (F16)
|
100% |
608
2.46 IPS |
|
|
Pose Estimation (I8)
|
80% |
606
2.45 IPS |
|
|
Object Detection (F32)
|
100% |
205
7.20 IPS |
|
|
Object Detection (F16)
|
99% |
247
8.66 IPS |
|
|
Object Detection (I8)
|
53% |
242
8.51 IPS |
|
|
Face Detection (F32)
|
100% |
622
7.15 IPS |
|
|
Face Detection (F16)
|
97% |
966
11.1 IPS |
|
|
Face Detection (I8)
|
75% |
858
9.86 IPS |
|
|
Text Classification (F32)
|
100% |
200
79.2 IPS |
|
|
Text Classification (F16)
|
98% |
248
98.0 IPS |
|
|
Machine Translation (F32)
|
100% |
322
49.6 IPS |
|
|
Machine Translation (F16)
|
100% |
321
49.4 IPS |
