| Upload Date | September 04 2025 03:13 PM |
| Views | 9 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | ARM ARMv8 |
| System Information | |
|---|---|
| Operating System | Android 16 |
| Model | Google Pixel 8a |
| Model ID | Google Pixel 8a |
| Motherboard | akita |
| 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 | 7.38 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
319
59.3 IPS |
|
|
Image Classification (HP)
|
100% |
535
99.5 IPS |
|
|
Image Classification (Q)
|
97% |
411
76.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
1316
21.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
1858
30.1 IPS |
|
|
Image Segmentation (Q)
|
98% |
1770
28.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
4923
5.74 IPS |
|
|
Pose Estimation (HP)
|
100% |
11909
13.9 IPS |
|
|
Pose Estimation (Q)
|
95% |
11699
13.7 IPS |
|
|
Object Detection (SP)
|
100% |
501
39.8 IPS |
|
|
Object Detection (HP)
|
99% |
623
49.5 IPS |
|
|
Object Detection (Q)
|
83% |
743
60.0 IPS |
|
|
Face Detection (SP)
|
100% |
2236
26.6 IPS |
|
|
Face Detection (HP)
|
100% |
2773
32.9 IPS |
|
|
Face Detection (Q)
|
96% |
2539
30.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
3246
25.0 IPS |
|
|
Depth Estimation (HP)
|
98% |
5474
42.3 IPS |
|
|
Depth Estimation (Q)
|
62% |
4340
41.2 IPS |
|
|
Style Transfer (SP)
|
100% |
7528
9.68 IPS |
|
|
Style Transfer (HP)
|
100% |
19527
25.1 IPS |
|
|
Style Transfer (Q)
|
98% |
18347
23.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1747
64.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2238
82.6 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
2078
77.0 IPS |
|
|
Text Classification (SP)
|
35% |
24
218.9 IPS |
|
|
Text Classification (HP)
|
35% |
30
273.1 IPS |
|
|
Text Classification (Q)
|
32% |
16
212.2 IPS |
|
|
Machine Translation (SP)
|
100% |
254
4.37 IPS |
|
|
Machine Translation (HP)
|
100% |
278
4.79 IPS |
|
|
Machine Translation (Q)
|
43% |
64
3.73 IPS |