Upload Date | August 22 2024 02:23 AM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Google Tensor |
System Information | |
---|---|
Operating System | Android 14 |
Model | Google Pixel 6a |
Model ID | Google Pixel 6a |
Motherboard | bluejay |
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 | 5.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
398
73.9 IPS |
|
Image Classification (HP)
|
100% |
387
72.0 IPS |
|
Image Classification (Q)
|
100% |
1175
218.5 IPS |
|
Image Segmentation (SP)
|
100% |
488
7.92 IPS |
|
Image Segmentation (HP)
|
100% |
475
7.70 IPS |
|
Image Segmentation (Q)
|
98% |
1250
20.3 IPS |
|
Pose Estimation (SP)
|
100% |
1777
2.07 IPS |
|
Pose Estimation (HP)
|
100% |
1724
2.01 IPS |
|
Pose Estimation (Q)
|
84% |
2278
2.70 IPS |
|
Object Detection (SP)
|
100% |
321
25.4 IPS |
|
Object Detection (HP)
|
100% |
321
25.5 IPS |
|
Object Detection (Q)
|
87% |
911
73.1 IPS |
|
Face Detection (SP)
|
100% |
1112
13.2 IPS |
|
Face Detection (HP)
|
100% |
1040
12.4 IPS |
|
Face Detection (Q)
|
95% |
2042
24.4 IPS |
|
Depth Estimation (SP)
|
100% |
1473
11.3 IPS |
|
Depth Estimation (HP)
|
100% |
1425
11.0 IPS |
|
Depth Estimation (Q)
|
75% |
2203
17.9 IPS |
|
Style Transfer (SP)
|
89% |
2561
3.32 IPS |
|
Style Transfer (HP)
|
89% |
2404
3.12 IPS |
|
Style Transfer (Q)
|
98% |
5182
6.68 IPS |
|
Image Super-Resolution (SP)
|
100% |
802
29.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
804
29.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
1296
48.0 IPS |
|
Text Classification (SP)
|
100% |
409
546.1 IPS |
|
Text Classification (HP)
|
100% |
407
543.7 IPS |
|
Text Classification (Q)
|
88% |
695
936.7 IPS |
|
Machine Translation (SP)
|
100% |
667
11.5 IPS |
|
Machine Translation (HP)
|
100% |
598
10.3 IPS |
|
Machine Translation (Q)
|
50% |
464
16.5 IPS |