Upload Date | September 07 2025 11:18 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Google Tensor G3 |
System Information | |
---|---|
Operating System | Android 16 |
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 | 10.92 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1468
273.0 IPS |
|
Image Classification (HP)
|
100% |
1445
268.8 IPS |
|
Image Classification (Q)
|
100% |
1793
333.4 IPS |
|
Image Segmentation (SP)
|
100% |
1665
27.0 IPS |
|
Image Segmentation (HP)
|
100% |
1351
21.9 IPS |
|
Image Segmentation (Q)
|
98% |
2158
35.1 IPS |
|
Pose Estimation (SP)
|
100% |
2246
2.62 IPS |
|
Pose Estimation (HP)
|
100% |
2004
2.34 IPS |
|
Pose Estimation (Q)
|
84% |
3872
4.59 IPS |
|
Object Detection (SP)
|
98% |
686
54.6 IPS |
|
Object Detection (HP)
|
98% |
700
55.7 IPS |
|
Object Detection (Q)
|
83% |
985
79.6 IPS |
|
Face Detection (SP)
|
100% |
1797
21.3 IPS |
|
Face Detection (HP)
|
100% |
2187
26.0 IPS |
|
Face Detection (Q)
|
95% |
3354
40.0 IPS |
|
Depth Estimation (SP)
|
99% |
2048
15.8 IPS |
|
Depth Estimation (HP)
|
99% |
2052
15.9 IPS |
|
Depth Estimation (Q)
|
64% |
3055
28.0 IPS |
|
Style Transfer (SP)
|
89% |
5013
6.51 IPS |
|
Style Transfer (HP)
|
89% |
4962
6.44 IPS |
|
Style Transfer (Q)
|
98% |
8042
10.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
784
28.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
761
28.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
1713
63.5 IPS |
|
Text Classification (SP)
|
100% |
286
381.9 IPS |
|
Text Classification (HP)
|
99% |
302
403.3 IPS |
|
Text Classification (Q)
|
88% |
374
504.0 IPS |
|
Machine Translation (SP)
|
100% |
956
16.5 IPS |
|
Machine Translation (HP)
|
100% |
930
16.0 IPS |
|
Machine Translation (Q)
|
50% |
460
16.3 IPS |