Upload Date | September 16 2024 11:42 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Google Tensor G3 |
System Information | |
---|---|
Operating System | Android 14 |
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 | 11.32 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1483
275.8 IPS |
|
Image Classification (HP)
|
100% |
1017
189.2 IPS |
|
Image Classification (Q)
|
100% |
2595
482.5 IPS |
|
Image Segmentation (SP)
|
100% |
1711
27.7 IPS |
|
Image Segmentation (HP)
|
100% |
649
10.5 IPS |
|
Image Segmentation (Q)
|
98% |
1023
16.6 IPS |
|
Pose Estimation (SP)
|
100% |
1580
1.84 IPS |
|
Pose Estimation (HP)
|
100% |
1610
1.88 IPS |
|
Pose Estimation (Q)
|
84% |
2971
3.52 IPS |
|
Object Detection (SP)
|
98% |
656
52.2 IPS |
|
Object Detection (HP)
|
98% |
617
49.1 IPS |
|
Object Detection (Q)
|
83% |
1092
88.2 IPS |
|
Face Detection (SP)
|
100% |
1189
14.1 IPS |
|
Face Detection (HP)
|
100% |
2886
34.3 IPS |
|
Face Detection (Q)
|
95% |
2326
27.8 IPS |
|
Depth Estimation (SP)
|
99% |
1551
12.0 IPS |
|
Depth Estimation (HP)
|
99% |
1579
12.2 IPS |
|
Depth Estimation (Q)
|
64% |
1910
17.5 IPS |
|
Style Transfer (SP)
|
89% |
2867
3.72 IPS |
|
Style Transfer (HP)
|
89% |
5321
6.91 IPS |
|
Style Transfer (Q)
|
98% |
9446
12.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
961
35.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
565
20.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
1297
48.1 IPS |
|
Text Classification (SP)
|
100% |
450
600.3 IPS |
|
Text Classification (HP)
|
99% |
258
344.9 IPS |
|
Text Classification (Q)
|
88% |
446
602.0 IPS |
|
Machine Translation (SP)
|
100% |
963
16.6 IPS |
|
Machine Translation (HP)
|
100% |
667
11.5 IPS |
|
Machine Translation (Q)
|
50% |
326
11.6 IPS |