User | nwisecup |
Upload Date | August 29 2024 11:38 PM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
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% |
246
45.7 IPS |
|
Image Classification (HP)
|
100% |
383
71.3 IPS |
|
Image Classification (Q)
|
97% |
379
70.7 IPS |
|
Image Segmentation (SP)
|
100% |
870
14.1 IPS |
|
Image Segmentation (HP)
|
100% |
983
15.9 IPS |
|
Image Segmentation (Q)
|
98% |
1002
16.3 IPS |
|
Pose Estimation (SP)
|
100% |
478
0.56 IPS |
|
Pose Estimation (HP)
|
100% |
664
0.78 IPS |
|
Pose Estimation (Q)
|
96% |
659
0.77 IPS |
|
Object Detection (SP)
|
100% |
256
20.3 IPS |
|
Object Detection (HP)
|
100% |
386
30.6 IPS |
|
Object Detection (Q)
|
92% |
317
25.3 IPS |
|
Face Detection (SP)
|
100% |
1192
14.2 IPS |
|
Face Detection (HP)
|
100% |
1475
17.5 IPS |
|
Face Detection (Q)
|
97% |
1108
13.2 IPS |
|
Depth Estimation (SP)
|
100% |
901
6.94 IPS |
|
Depth Estimation (HP)
|
99% |
1096
8.44 IPS |
|
Depth Estimation (Q)
|
72% |
991
8.21 IPS |
|
Style Transfer (SP)
|
100% |
2506
3.22 IPS |
|
Style Transfer (HP)
|
100% |
3281
4.22 IPS |
|
Style Transfer (Q)
|
98% |
3186
4.11 IPS |
|
Image Super-Resolution (SP)
|
100% |
456
16.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
535
19.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
531
19.7 IPS |
|
Text Classification (SP)
|
100% |
432
576.8 IPS |
|
Text Classification (HP)
|
100% |
433
578.0 IPS |
|
Text Classification (Q)
|
91% |
630
846.3 IPS |
|
Machine Translation (SP)
|
100% |
615
10.6 IPS |
|
Machine Translation (HP)
|
100% |
614
10.6 IPS |
|
Machine Translation (Q)
|
57% |
401
9.81 IPS |