Upload Date | September 19 2024 06:00 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Google Tensor |
System Information | |
---|---|
Operating System | Android 14 |
Model | Google Pixel 6 Pro |
Model ID | Google Pixel 6 Pro |
Motherboard | raven |
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 @ 2.25 GHz |
Cluster 3 | 2 Cores @ 2.80 GHz |
Memory Information | |
---|---|
Size | 11.28 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
286
53.3 IPS |
|
Image Classification (HP)
|
100% |
421
78.4 IPS |
|
Image Classification (Q)
|
99% |
459
85.5 IPS |
|
Image Segmentation (SP)
|
100% |
582
9.44 IPS |
|
Image Segmentation (HP)
|
100% |
853
13.8 IPS |
|
Image Segmentation (Q)
|
98% |
965
15.7 IPS |
|
Pose Estimation (SP)
|
100% |
338
0.39 IPS |
|
Pose Estimation (HP)
|
100% |
434
0.51 IPS |
|
Pose Estimation (Q)
|
96% |
431
0.51 IPS |
|
Object Detection (SP)
|
100% |
300
23.8 IPS |
|
Object Detection (HP)
|
100% |
361
28.7 IPS |
|
Object Detection (Q)
|
83% |
372
30.1 IPS |
|
Face Detection (SP)
|
100% |
1364
16.2 IPS |
|
Face Detection (HP)
|
100% |
1955
23.2 IPS |
|
Face Detection (Q)
|
97% |
1761
21.0 IPS |
|
Depth Estimation (SP)
|
100% |
529
4.07 IPS |
|
Depth Estimation (HP)
|
99% |
633
4.87 IPS |
|
Depth Estimation (Q)
|
62% |
499
4.72 IPS |
|
Style Transfer (SP)
|
100% |
1403
1.80 IPS |
|
Style Transfer (HP)
|
100% |
2495
3.21 IPS |
|
Style Transfer (Q)
|
98% |
2441
3.15 IPS |
|
Image Super-Resolution (SP)
|
100% |
334
12.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
470
17.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
449
16.6 IPS |
|
Text Classification (SP)
|
100% |
269
359.6 IPS |
|
Text Classification (HP)
|
100% |
263
351.2 IPS |
|
Text Classification (Q)
|
91% |
514
691.2 IPS |
|
Machine Translation (SP)
|
100% |
408
7.02 IPS |
|
Machine Translation (HP)
|
100% |
398
6.86 IPS |
|
Machine Translation (Q)
|
57% |
299
7.31 IPS |