User | kitsunechan_2525 |
Upload Date | May 18 2025 05:16 PM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Google Tensor |
System Information | |
---|---|
Operating System | Android 16 |
Model | Google Pixel 6 |
Model ID | Google Pixel 6 |
Motherboard | oriole |
Governor | powersave |
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 | 7.41 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
316
58.8 IPS |
|
Image Classification (HP)
|
100% |
497
92.5 IPS |
|
Image Classification (Q)
|
99% |
441
82.3 IPS |
|
Image Segmentation (SP)
|
100% |
700
11.3 IPS |
|
Image Segmentation (HP)
|
100% |
1021
16.6 IPS |
|
Image Segmentation (Q)
|
98% |
978
15.9 IPS |
|
Pose Estimation (SP)
|
100% |
343
0.40 IPS |
|
Pose Estimation (HP)
|
100% |
438
0.51 IPS |
|
Pose Estimation (Q)
|
96% |
435
0.51 IPS |
|
Object Detection (SP)
|
100% |
360
28.6 IPS |
|
Object Detection (HP)
|
100% |
537
42.6 IPS |
|
Object Detection (Q)
|
83% |
513
41.5 IPS |
|
Face Detection (SP)
|
100% |
1541
18.3 IPS |
|
Face Detection (HP)
|
100% |
2121
25.2 IPS |
|
Face Detection (Q)
|
97% |
2017
24.1 IPS |
|
Depth Estimation (SP)
|
100% |
662
5.10 IPS |
|
Depth Estimation (HP)
|
99% |
828
6.38 IPS |
|
Depth Estimation (Q)
|
62% |
666
6.30 IPS |
|
Style Transfer (SP)
|
100% |
1459
1.88 IPS |
|
Style Transfer (HP)
|
100% |
2629
3.38 IPS |
|
Style Transfer (Q)
|
98% |
2612
3.37 IPS |
|
Image Super-Resolution (SP)
|
100% |
412
15.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
620
22.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
621
23.0 IPS |
|
Text Classification (SP)
|
100% |
156
208.0 IPS |
|
Text Classification (HP)
|
100% |
159
212.8 IPS |
|
Text Classification (Q)
|
91% |
358
481.8 IPS |
|
Machine Translation (SP)
|
100% |
265
4.57 IPS |
|
Machine Translation (HP)
|
100% |
264
4.55 IPS |
|
Machine Translation (Q)
|
57% |
254
6.21 IPS |