Upload Date | August 24 2024 03:30 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Google Tensor |
System Information | |
---|---|
Operating System | Android 15 |
Model | Google Pixel 6a |
Model ID | Google Pixel 6a |
Motherboard | bluejay |
Governor | sched_pixel |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.25 GHz |
Cluster 3 | 2 Cores @ 2.80 GHz |
Memory Information | |
---|---|
Size | 5.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
218
40.5 IPS |
|
Image Classification (HP)
|
100% |
4417
821.5 IPS |
|
Image Classification (Q)
|
99% |
7069
1.32 KIPS |
|
Image Segmentation (SP)
|
100% |
270
4.38 IPS |
|
Image Segmentation (HP)
|
100% |
3413
55.3 IPS |
|
Image Segmentation (Q)
|
98% |
2085
33.9 IPS |
|
Pose Estimation (SP)
|
100% |
350
0.41 IPS |
|
Pose Estimation (HP)
|
100% |
18874
22.0 IPS |
|
Pose Estimation (Q)
|
97% |
43960
51.5 IPS |
|
Object Detection (SP)
|
100% |
174
13.8 IPS |
|
Object Detection (HP)
|
100% |
176
14.0 IPS |
|
Object Detection (Q)
|
89% |
523
41.9 IPS |
|
Face Detection (SP)
|
100% |
441
5.24 IPS |
|
Face Detection (HP)
|
100% |
9538
113.3 IPS |
|
Face Detection (Q)
|
97% |
18274
217.9 IPS |
|
Depth Estimation (SP)
|
100% |
371
2.86 IPS |
|
Depth Estimation (HP)
|
99% |
16345
125.9 IPS |
|
Depth Estimation (Q)
|
70% |
24690
208.0 IPS |
|
Style Transfer (SP)
|
100% |
627
0.81 IPS |
|
Style Transfer (HP)
|
100% |
628
0.81 IPS |
|
Style Transfer (Q)
|
98% |
2711
3.50 IPS |
|
Image Super-Resolution (SP)
|
100% |
186
6.85 IPS |
|
Image Super-Resolution (HP)
|
100% |
187
6.92 IPS |
|
Image Super-Resolution (Q)
|
97% |
10942
405.5 IPS |
|
Text Classification (SP)
|
100% |
214
286.2 IPS |
|
Text Classification (HP)
|
100% |
215
287.0 IPS |
|
Text Classification (Q)
|
92% |
1555
2.09 KIPS |
|
Machine Translation (SP)
|
100% |
348
5.99 IPS |
|
Machine Translation (HP)
|
100% |
351
6.05 IPS |
|
Machine Translation (Q)
|
57% |
251
6.14 IPS |