Upload Date | January 06 2025 11:18 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Google Tensor G2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Google Pixel 7 Pro |
Model ID | Google Pixel 7 Pro |
Motherboard | cheetah |
Governor | sched_pixel |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.35 GHz |
Cluster 3 | 2 Cores @ 2.85 GHz |
Memory Information | |
---|---|
Size | 11.17 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
519
96.5 IPS |
|
Image Classification (HP)
|
100% |
523
97.3 IPS |
|
Image Classification (Q)
|
100% |
1531
284.7 IPS |
|
Image Segmentation (SP)
|
100% |
640
10.4 IPS |
|
Image Segmentation (HP)
|
100% |
636
10.3 IPS |
|
Image Segmentation (Q)
|
98% |
1716
27.9 IPS |
|
Pose Estimation (SP)
|
100% |
2410
2.81 IPS |
|
Pose Estimation (HP)
|
100% |
2354
2.75 IPS |
|
Pose Estimation (Q)
|
84% |
3281
3.89 IPS |
|
Object Detection (SP)
|
100% |
411
32.6 IPS |
|
Object Detection (HP)
|
100% |
432
34.2 IPS |
|
Object Detection (Q)
|
83% |
1225
99.0 IPS |
|
Face Detection (SP)
|
100% |
1467
17.4 IPS |
|
Face Detection (HP)
|
100% |
1450
17.2 IPS |
|
Face Detection (Q)
|
95% |
2890
34.5 IPS |
|
Depth Estimation (SP)
|
100% |
1732
13.3 IPS |
|
Depth Estimation (HP)
|
99% |
1723
13.3 IPS |
|
Depth Estimation (Q)
|
64% |
2818
25.8 IPS |
|
Style Transfer (SP)
|
89% |
3546
4.60 IPS |
|
Style Transfer (HP)
|
89% |
3463
4.50 IPS |
|
Style Transfer (Q)
|
98% |
7250
9.35 IPS |
|
Image Super-Resolution (SP)
|
100% |
990
36.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
1010
37.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
1828
67.7 IPS |
|
Text Classification (SP)
|
100% |
484
645.8 IPS |
|
Text Classification (HP)
|
100% |
523
697.6 IPS |
|
Text Classification (Q)
|
88% |
844
1.14 KIPS |
|
Machine Translation (SP)
|
100% |
754
13.0 IPS |
|
Machine Translation (HP)
|
100% |
710
12.2 IPS |
|
Machine Translation (Q)
|
50% |
369
13.1 IPS |