| Upload Date | October 04 2025 09:56 AM |
| Views | 3 |
| 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 | 7.14 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
288
53.5 IPS |
|
|
Image Classification (HP)
|
100% |
432
80.4 IPS |
|
|
Image Classification (Q)
|
97% |
402
75.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
1361
22.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
1966
31.9 IPS |
|
|
Image Segmentation (Q)
|
98% |
1650
26.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
4894
5.71 IPS |
|
|
Pose Estimation (HP)
|
100% |
12365
14.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
11954
14.0 IPS |
|
|
Object Detection (SP)
|
100% |
514
40.8 IPS |
|
|
Object Detection (HP)
|
99% |
822
65.2 IPS |
|
|
Object Detection (Q)
|
83% |
504
40.7 IPS |
|
|
Face Detection (SP)
|
100% |
1780
21.1 IPS |
|
|
Face Detection (HP)
|
100% |
2428
28.9 IPS |
|
|
Face Detection (Q)
|
96% |
2148
25.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
3297
25.4 IPS |
|
|
Depth Estimation (HP)
|
98% |
5571
43.1 IPS |
|
|
Depth Estimation (Q)
|
62% |
4404
41.8 IPS |
|
|
Style Transfer (SP)
|
100% |
7482
9.62 IPS |
|
|
Style Transfer (HP)
|
100% |
19528
25.1 IPS |
|
|
Style Transfer (Q)
|
98% |
18459
23.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1716
63.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2163
79.9 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
1992
73.8 IPS |
|
|
Text Classification (SP)
|
35% |
15
137.0 IPS |
|
|
Text Classification (HP)
|
35% |
17
153.3 IPS |
|
|
Text Classification (Q)
|
32% |
11
140.3 IPS |
|
|
Machine Translation (SP)
|
100% |
254
4.38 IPS |
|
|
Machine Translation (HP)
|
100% |
271
4.67 IPS |
|
|
Machine Translation (Q)
|
43% |
64
3.71 IPS |