Upload Date | January 02 2025 09:34 AM |
Views | 1 |
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% |
1626
302.4 IPS |
|
Image Classification (HP)
|
100% |
1578
293.4 IPS |
|
Image Classification (Q)
|
100% |
2601
483.7 IPS |
|
Image Segmentation (SP)
|
100% |
1806
29.3 IPS |
|
Image Segmentation (HP)
|
100% |
1811
29.4 IPS |
|
Image Segmentation (Q)
|
98% |
2633
42.8 IPS |
|
Pose Estimation (SP)
|
100% |
3065
3.58 IPS |
|
Pose Estimation (HP)
|
100% |
2843
3.32 IPS |
|
Pose Estimation (Q)
|
84% |
6477
7.68 IPS |
|
Object Detection (SP)
|
98% |
1409
112.1 IPS |
|
Object Detection (HP)
|
98% |
1429
113.7 IPS |
|
Object Detection (Q)
|
83% |
2359
190.6 IPS |
|
Face Detection (SP)
|
100% |
3009
35.8 IPS |
|
Face Detection (HP)
|
100% |
3039
36.1 IPS |
|
Face Detection (Q)
|
95% |
5460
65.2 IPS |
|
Depth Estimation (SP)
|
99% |
2774
21.4 IPS |
|
Depth Estimation (HP)
|
99% |
2818
21.8 IPS |
|
Depth Estimation (Q)
|
64% |
5199
47.6 IPS |
|
Style Transfer (SP)
|
89% |
6839
8.88 IPS |
|
Style Transfer (HP)
|
89% |
6912
8.97 IPS |
|
Style Transfer (Q)
|
98% |
13682
17.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
1400
51.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
1420
52.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
3768
139.6 IPS |
|
Text Classification (SP)
|
100% |
687
916.5 IPS |
|
Text Classification (HP)
|
99% |
750
1.00 KIPS |
|
Text Classification (Q)
|
88% |
1107
1.49 KIPS |
|
Machine Translation (SP)
|
100% |
1300
22.4 IPS |
|
Machine Translation (HP)
|
100% |
1275
22.0 IPS |
|
Machine Translation (Q)
|
50% |
630
22.4 IPS |