Upload Date | January 06 2025 11:31 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
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% |
269
50.0 IPS |
|
Image Classification (HP)
|
100% |
3630
675.1 IPS |
|
Image Classification (Q)
|
99% |
5206
971.0 IPS |
|
Image Segmentation (SP)
|
100% |
303
4.92 IPS |
|
Image Segmentation (HP)
|
100% |
8242
133.6 IPS |
|
Image Segmentation (Q)
|
98% |
13910
226.2 IPS |
|
Pose Estimation (SP)
|
100% |
394
0.46 IPS |
|
Pose Estimation (HP)
|
100% |
31339
36.6 IPS |
|
Pose Estimation (Q)
|
97% |
62076
72.7 IPS |
|
Object Detection (SP)
|
100% |
246
19.5 IPS |
|
Object Detection (HP)
|
100% |
3941
312.6 IPS |
|
Object Detection (Q)
|
87% |
4589
368.1 IPS |
|
Face Detection (SP)
|
100% |
587
6.98 IPS |
|
Face Detection (HP)
|
100% |
14784
175.7 IPS |
|
Face Detection (Q)
|
97% |
32302
385.1 IPS |
|
Depth Estimation (SP)
|
100% |
529
4.07 IPS |
|
Depth Estimation (HP)
|
99% |
29851
230.0 IPS |
|
Depth Estimation (Q)
|
64% |
34120
314.1 IPS |
|
Style Transfer (SP)
|
100% |
813
1.04 IPS |
|
Style Transfer (HP)
|
100% |
780
1.00 IPS |
|
Style Transfer (Q)
|
73% |
2862
3.92 IPS |
|
Image Super-Resolution (SP)
|
100% |
274
10.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
8332
307.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
13816
511.9 IPS |
|
Text Classification (SP)
|
100% |
351
468.7 IPS |
|
Text Classification (HP)
|
100% |
351
468.4 IPS |
|
Text Classification (Q)
|
92% |
929
1.25 KIPS |
|
Machine Translation (SP)
|
100% |
548
9.43 IPS |
|
Machine Translation (HP)
|
100% |
522
8.99 IPS |
|
Machine Translation (Q)
|
57% |
355
8.68 IPS |