Upload Date | September 16 2024 01:55 PM |
Views | 2 |
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% |
1422
264.5 IPS |
|
Image Classification (HP)
|
100% |
614
114.1 IPS |
|
Image Classification (Q)
|
100% |
2393
444.9 IPS |
|
Image Segmentation (SP)
|
100% |
1209
19.6 IPS |
|
Image Segmentation (HP)
|
100% |
695
11.3 IPS |
|
Image Segmentation (Q)
|
98% |
1039
16.9 IPS |
|
Pose Estimation (SP)
|
100% |
1630
1.90 IPS |
|
Pose Estimation (HP)
|
100% |
1622
1.89 IPS |
|
Pose Estimation (Q)
|
84% |
2716
3.22 IPS |
|
Object Detection (SP)
|
99% |
489
38.8 IPS |
|
Object Detection (HP)
|
99% |
858
68.2 IPS |
|
Object Detection (Q)
|
83% |
1297
104.7 IPS |
|
Face Detection (SP)
|
100% |
2269
27.0 IPS |
|
Face Detection (HP)
|
100% |
2234
26.5 IPS |
|
Face Detection (Q)
|
95% |
3244
38.7 IPS |
|
Depth Estimation (SP)
|
99% |
1189
9.19 IPS |
|
Depth Estimation (HP)
|
99% |
1928
14.9 IPS |
|
Depth Estimation (Q)
|
64% |
3184
29.2 IPS |
|
Style Transfer (SP)
|
89% |
4952
6.43 IPS |
|
Style Transfer (HP)
|
89% |
5088
6.60 IPS |
|
Style Transfer (Q)
|
98% |
5495
7.09 IPS |
|
Image Super-Resolution (SP)
|
100% |
597
22.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
1035
38.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
1394
51.7 IPS |
|
Text Classification (SP)
|
100% |
289
385.7 IPS |
|
Text Classification (HP)
|
99% |
365
486.8 IPS |
|
Text Classification (Q)
|
88% |
651
878.2 IPS |
|
Machine Translation (SP)
|
100% |
583
10.0 IPS |
|
Machine Translation (HP)
|
100% |
897
15.5 IPS |
|
Machine Translation (Q)
|
50% |
319
11.3 IPS |