| User | PanisSupraOmnia |
| Upload Date | August 22 2024 05:44 PM |
| Views | 6 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Google Tensor G3 |
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | Google Pixel 8 Pro |
| Model ID | Google Pixel 8 Pro |
| Motherboard | husky |
| Governor | sched_pixel |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 9 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
| Base Frequency | 1.70 GHz |
| Cluster 1 | 4 Cores @ 1.70 GHz |
| Cluster 2 | 4 Cores @ 2.37 GHz |
| Cluster 3 | 1 Core @ 2.91 GHz |
| Memory Information | |
|---|---|
| Size | 11.32 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
789
146.8 IPS |
|
|
Image Classification (HP)
|
100% |
575
106.9 IPS |
|
|
Image Classification (Q)
|
100% |
986
183.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
1702
27.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
623
10.1 IPS |
|
|
Image Segmentation (Q)
|
98% |
2881
46.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
2965
3.46 IPS |
|
|
Pose Estimation (HP)
|
100% |
2773
3.24 IPS |
|
|
Pose Estimation (Q)
|
84% |
6322
7.50 IPS |
|
|
Object Detection (SP)
|
98% |
868
69.1 IPS |
|
|
Object Detection (HP)
|
98% |
860
68.4 IPS |
|
|
Object Detection (Q)
|
87% |
1031
82.8 IPS |
|
|
Face Detection (SP)
|
100% |
1655
19.7 IPS |
|
|
Face Detection (HP)
|
100% |
2142
25.4 IPS |
|
|
Face Detection (Q)
|
95% |
2252
26.9 IPS |
|
|
Depth Estimation (SP)
|
99% |
1324
10.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
1484
11.5 IPS |
|
|
Depth Estimation (Q)
|
75% |
2525
20.5 IPS |
|
|
Style Transfer (SP)
|
89% |
5717
7.42 IPS |
|
|
Style Transfer (HP)
|
89% |
2733
3.55 IPS |
|
|
Style Transfer (Q)
|
98% |
10825
14.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
970
35.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
673
24.9 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
1206
44.7 IPS |
|
|
Text Classification (SP)
|
100% |
245
327.6 IPS |
|
|
Text Classification (HP)
|
99% |
242
323.1 IPS |
|
|
Text Classification (Q)
|
88% |
439
591.7 IPS |
|
|
Machine Translation (SP)
|
100% |
610
10.5 IPS |
|
|
Machine Translation (HP)
|
100% |
823
14.2 IPS |
|
|
Machine Translation (Q)
|
50% |
324
11.5 IPS |