Google Pixel 4
Geekbench ML Score
309
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | October 02 2023 10:50 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Google Pixel 4 |
| Model ID | Google Pixel 4 |
| Motherboard | flame |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | Qualcomm Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 81 architecture 8 variant 13 part 2052 revision 14 |
| Base Frequency | 1.78 GHz |
| Cluster 1 | 4 Cores @ 1.79 GHz |
| Cluster 2 | 3 Cores @ 2.42 GHz |
| Cluster 3 | 1 Core @ 2.84 GHz |
| Memory Information | |
|---|---|
| Size | 5.34 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
340
36.4 IPS |
|
|
Image Classification (F16)
|
100% |
316
33.8 IPS |
|
|
Image Classification (I8)
|
81% |
169
18.1 IPS |
|
|
Image Segmentation (F32)
|
100% |
404
2.50 IPS |
|
|
Image Segmentation (F16)
|
100% |
401
2.48 IPS |
|
|
Image Segmentation (I8)
|
89% |
668
4.13 IPS |
|
|
Pose Estimation (F32)
|
100% |
208
0.84 IPS |
|
|
Pose Estimation (F16)
|
100% |
201
0.82 IPS |
|
|
Pose Estimation (I8)
|
80% |
176
0.71 IPS |
|
|
Object Detection (F32)
|
100% |
322
11.3 IPS |
|
|
Object Detection (F16)
|
100% |
310
10.9 IPS |
|
|
Object Detection (I8)
|
52% |
245
8.59 IPS |
|
|
Face Detection (F32)
|
100% |
484
5.56 IPS |
|
|
Face Detection (F16)
|
100% |
480
5.52 IPS |
|
|
Face Detection (I8)
|
75% |
452
5.19 IPS |
|
|
Text Classification (F32)
|
100% |
191
75.6 IPS |
|
|
Text Classification (F16)
|
100% |
225
89.1 IPS |
|
|
Machine Translation (F32)
|
100% |
351
54.0 IPS |
|
|
Machine Translation (F16)
|
100% |
377
58.1 IPS |
