Google Pixel 4
Geekbench ML Score
436
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | March 28 2024 04:14 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 | GPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
208
38.9 IPS |
|
|
Image Classification (F16)
|
100% |
359
67.2 IPS |
|
|
Image Classification (I8)
|
97% |
370
69.2 IPS |
|
|
Image Segmentation (F32)
|
100% |
273
4.57 IPS |
|
|
Image Segmentation (F16)
|
100% |
522
8.71 IPS |
|
|
Image Segmentation (I8)
|
98% |
525
8.77 IPS |
|
|
Pose Estimation (F32)
|
100% |
416
0.50 IPS |
|
|
Pose Estimation (F16)
|
100% |
316
0.38 IPS |
|
|
Pose Estimation (I8)
|
100% |
315
0.38 IPS |
|
|
Object Detection (F32)
|
100% |
167
12.5 IPS |
|
|
Object Detection (F16)
|
100% |
217
16.2 IPS |
|
|
Object Detection (I8)
|
62% |
207
15.4 IPS |
|
|
Face Detection (F32)
|
100% |
480
5.71 IPS |
|
|
Face Detection (F16)
|
97% |
1101
13.1 IPS |
|
|
Face Detection (I8)
|
87% |
1197
14.2 IPS |
|
|
Depth Estimation (F32)
|
100% |
464
3.60 IPS |
|
|
Depth Estimation (F16)
|
100% |
928
7.20 IPS |
|
|
Depth Estimation (I8)
|
95% |
934
7.24 IPS |
|
|
Style Transfer (F32)
|
100% |
945
1.24 IPS |
|
|
Style Transfer (F16)
|
100% |
2354
3.10 IPS |
|
|
Style Transfer (I8)
|
98% |
2289
3.01 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
239
8.54 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
449
16.0 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
442
15.8 IPS |
|
|
Text Classification (F32)
|
100% |
166
238.1 IPS |
|
|
Text Classification (F16)
|
100% |
194
279.5 IPS |
|
|
Text Classification (I8)
|
92% |
317
455.9 IPS |
|
|
Machine Translation (F32)
|
100% |
341
6.28 IPS |
|
|
Machine Translation (F16)
|
100% |
352
6.47 IPS |
|
|
Machine Translation (I8)
|
64% |
334
6.14 IPS |
