Upload Date | September 18 2024 02:15 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
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 | 7.42 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
344
64.0 IPS |
|
Image Classification (HP)
|
100% |
383
71.3 IPS |
|
Image Classification (Q)
|
99% |
353
65.8 IPS |
|
Image Segmentation (SP)
|
100% |
876
14.2 IPS |
|
Image Segmentation (HP)
|
100% |
993
16.1 IPS |
|
Image Segmentation (Q)
|
98% |
945
15.4 IPS |
|
Pose Estimation (SP)
|
100% |
478
0.56 IPS |
|
Pose Estimation (HP)
|
100% |
665
0.78 IPS |
|
Pose Estimation (Q)
|
96% |
660
0.77 IPS |
|
Object Detection (SP)
|
100% |
271
21.5 IPS |
|
Object Detection (HP)
|
100% |
298
23.6 IPS |
|
Object Detection (Q)
|
83% |
332
26.8 IPS |
|
Face Detection (SP)
|
100% |
1141
13.6 IPS |
|
Face Detection (HP)
|
100% |
1206
14.3 IPS |
|
Face Detection (Q)
|
97% |
1183
14.1 IPS |
|
Depth Estimation (SP)
|
100% |
906
6.98 IPS |
|
Depth Estimation (HP)
|
99% |
1098
8.46 IPS |
|
Depth Estimation (Q)
|
62% |
895
8.48 IPS |
|
Style Transfer (SP)
|
100% |
2464
3.17 IPS |
|
Style Transfer (HP)
|
100% |
3204
4.12 IPS |
|
Style Transfer (Q)
|
98% |
3247
4.19 IPS |
|
Image Super-Resolution (SP)
|
100% |
445
16.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
512
18.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
504
18.7 IPS |
|
Text Classification (SP)
|
100% |
346
461.2 IPS |
|
Text Classification (HP)
|
100% |
358
478.0 IPS |
|
Text Classification (Q)
|
91% |
560
752.5 IPS |
|
Machine Translation (SP)
|
100% |
523
9.01 IPS |
|
Machine Translation (HP)
|
100% |
508
8.75 IPS |
|
Machine Translation (Q)
|
57% |
331
8.10 IPS |