Upload Date | November 21 2024 06:55 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Google Tensor G2 |
System Information | |
---|---|
Operating System | Android 15 |
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 | 11.20 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
527
98.1 IPS |
|
Image Classification (HP)
|
100% |
512
95.2 IPS |
|
Image Classification (Q)
|
100% |
1438
267.3 IPS |
|
Image Segmentation (SP)
|
100% |
635
10.3 IPS |
|
Image Segmentation (HP)
|
100% |
639
10.4 IPS |
|
Image Segmentation (Q)
|
98% |
1698
27.6 IPS |
|
Pose Estimation (SP)
|
100% |
2357
2.75 IPS |
|
Pose Estimation (HP)
|
100% |
2359
2.75 IPS |
|
Pose Estimation (Q)
|
84% |
3576
4.24 IPS |
|
Object Detection (SP)
|
100% |
501
39.7 IPS |
|
Object Detection (HP)
|
100% |
452
35.8 IPS |
|
Object Detection (Q)
|
83% |
1243
100.4 IPS |
|
Face Detection (SP)
|
100% |
1332
15.8 IPS |
|
Face Detection (HP)
|
100% |
1328
15.8 IPS |
|
Face Detection (Q)
|
95% |
3144
37.5 IPS |
|
Depth Estimation (SP)
|
100% |
1733
13.4 IPS |
|
Depth Estimation (HP)
|
99% |
1704
13.1 IPS |
|
Depth Estimation (Q)
|
64% |
2820
25.8 IPS |
|
Style Transfer (SP)
|
89% |
3570
4.63 IPS |
|
Style Transfer (HP)
|
89% |
3277
4.25 IPS |
|
Style Transfer (Q)
|
98% |
7253
9.35 IPS |
|
Image Super-Resolution (SP)
|
100% |
967
35.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
986
36.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
1821
67.5 IPS |
|
Text Classification (SP)
|
100% |
475
634.5 IPS |
|
Text Classification (HP)
|
100% |
486
648.4 IPS |
|
Text Classification (Q)
|
88% |
777
1.05 KIPS |
|
Machine Translation (SP)
|
100% |
771
13.3 IPS |
|
Machine Translation (HP)
|
100% |
689
11.9 IPS |
|
Machine Translation (Q)
|
50% |
418
14.8 IPS |