Upload Date | December 21 2024 10:13 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Google Tensor G3 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Google Pixel 8 |
Model ID | Google Pixel 8 |
Motherboard | shiba |
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 | 7.42 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
850
158.2 IPS |
|
Image Classification (HP)
|
100% |
1420
264.1 IPS |
|
Image Classification (Q)
|
100% |
2359
438.7 IPS |
|
Image Segmentation (SP)
|
100% |
1039
16.8 IPS |
|
Image Segmentation (HP)
|
100% |
1272
20.6 IPS |
|
Image Segmentation (Q)
|
98% |
2564
41.7 IPS |
|
Pose Estimation (SP)
|
100% |
2987
3.49 IPS |
|
Pose Estimation (HP)
|
100% |
2761
3.22 IPS |
|
Pose Estimation (Q)
|
84% |
5918
7.02 IPS |
|
Object Detection (SP)
|
98% |
1338
106.5 IPS |
|
Object Detection (HP)
|
98% |
853
67.8 IPS |
|
Object Detection (Q)
|
83% |
2340
189.1 IPS |
|
Face Detection (SP)
|
100% |
2934
34.9 IPS |
|
Face Detection (HP)
|
100% |
2107
25.0 IPS |
|
Face Detection (Q)
|
95% |
5001
59.7 IPS |
|
Depth Estimation (SP)
|
99% |
2800
21.6 IPS |
|
Depth Estimation (HP)
|
99% |
2684
20.7 IPS |
|
Depth Estimation (Q)
|
64% |
4654
42.6 IPS |
|
Style Transfer (SP)
|
89% |
6326
8.21 IPS |
|
Style Transfer (HP)
|
89% |
5628
7.31 IPS |
|
Style Transfer (Q)
|
98% |
12134
15.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
1143
42.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
1112
41.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
2715
100.6 IPS |
|
Text Classification (SP)
|
100% |
443
591.5 IPS |
|
Text Classification (HP)
|
99% |
479
638.8 IPS |
|
Text Classification (Q)
|
88% |
795
1.07 KIPS |
|
Machine Translation (SP)
|
100% |
1036
17.9 IPS |
|
Machine Translation (HP)
|
100% |
944
16.3 IPS |
|
Machine Translation (Q)
|
50% |
468
16.6 IPS |