User | M91 |
Upload Date | November 19 2024 01:37 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
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% |
1477
274.7 IPS |
|
Image Classification (HP)
|
100% |
1047
194.7 IPS |
|
Image Classification (Q)
|
100% |
2256
419.5 IPS |
|
Image Segmentation (SP)
|
100% |
1553
25.2 IPS |
|
Image Segmentation (HP)
|
100% |
1521
24.7 IPS |
|
Image Segmentation (Q)
|
98% |
2354
38.3 IPS |
|
Pose Estimation (SP)
|
100% |
2538
2.96 IPS |
|
Pose Estimation (HP)
|
100% |
2161
2.52 IPS |
|
Pose Estimation (Q)
|
84% |
3902
4.63 IPS |
|
Object Detection (SP)
|
98% |
659
52.5 IPS |
|
Object Detection (HP)
|
98% |
660
52.5 IPS |
|
Object Detection (Q)
|
83% |
1015
82.0 IPS |
|
Face Detection (SP)
|
100% |
1610
19.1 IPS |
|
Face Detection (HP)
|
100% |
1628
19.3 IPS |
|
Face Detection (Q)
|
95% |
2390
28.5 IPS |
|
Depth Estimation (SP)
|
99% |
1452
11.2 IPS |
|
Depth Estimation (HP)
|
99% |
1532
11.8 IPS |
|
Depth Estimation (Q)
|
64% |
2374
21.7 IPS |
|
Style Transfer (SP)
|
89% |
3860
5.01 IPS |
|
Style Transfer (HP)
|
89% |
3642
4.73 IPS |
|
Style Transfer (Q)
|
98% |
6920
8.92 IPS |
|
Image Super-Resolution (SP)
|
100% |
709
26.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
733
27.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
1732
64.2 IPS |
|
Text Classification (SP)
|
100% |
453
604.1 IPS |
|
Text Classification (HP)
|
99% |
456
609.2 IPS |
|
Text Classification (Q)
|
88% |
744
1.00 KIPS |
|
Machine Translation (SP)
|
100% |
1068
18.4 IPS |
|
Machine Translation (HP)
|
100% |
997
17.2 IPS |
|
Machine Translation (Q)
|
50% |
470
16.7 IPS |