Upload Date | April 13 2025 01:40 PM |
Views | 1 |
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 | 7.38 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
240
44.6 IPS |
|
Image Classification (HP)
|
100% |
4082
759.1 IPS |
|
Image Classification (Q)
|
99% |
5947
1.11 KIPS |
|
Image Segmentation (SP)
|
100% |
291
4.71 IPS |
|
Image Segmentation (HP)
|
100% |
6123
99.3 IPS |
|
Image Segmentation (Q)
|
98% |
15274
248.4 IPS |
|
Pose Estimation (SP)
|
100% |
289
0.34 IPS |
|
Pose Estimation (HP)
|
100% |
30939
36.1 IPS |
|
Pose Estimation (Q)
|
97% |
62861
73.6 IPS |
|
Object Detection (SP)
|
100% |
203
16.1 IPS |
|
Object Detection (HP)
|
100% |
4264
338.2 IPS |
|
Object Detection (Q)
|
87% |
5336
428.0 IPS |
|
Face Detection (SP)
|
100% |
479
5.69 IPS |
|
Face Detection (HP)
|
100% |
15760
187.3 IPS |
|
Face Detection (Q)
|
97% |
26822
319.8 IPS |
|
Depth Estimation (SP)
|
100% |
419
3.23 IPS |
|
Depth Estimation (HP)
|
99% |
28771
221.7 IPS |
|
Depth Estimation (Q)
|
64% |
34451
317.1 IPS |
|
Style Transfer (SP)
|
100% |
570
0.73 IPS |
|
Style Transfer (HP)
|
100% |
575
0.74 IPS |
|
Style Transfer (Q)
|
73% |
2662
3.65 IPS |
|
Image Super-Resolution (SP)
|
100% |
220
8.13 IPS |
|
Image Super-Resolution (HP)
|
100% |
8880
327.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
15071
558.4 IPS |
|
Text Classification (SP)
|
100% |
320
426.6 IPS |
|
Text Classification (HP)
|
100% |
323
431.5 IPS |
|
Text Classification (Q)
|
92% |
1486
2.00 KIPS |
|
Machine Translation (SP)
|
100% |
451
7.77 IPS |
|
Machine Translation (HP)
|
100% |
401
6.92 IPS |
|
Machine Translation (Q)
|
57% |
290
7.09 IPS |