Upload Date | December 26 2024 05:50 AM |
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% |
217
40.3 IPS |
|
Image Classification (HP)
|
100% |
4289
797.7 IPS |
|
Image Classification (Q)
|
99% |
6989
1.30 KIPS |
|
Image Segmentation (SP)
|
100% |
261
4.24 IPS |
|
Image Segmentation (HP)
|
100% |
3411
55.3 IPS |
|
Image Segmentation (Q)
|
98% |
9302
151.3 IPS |
|
Pose Estimation (SP)
|
100% |
335
0.39 IPS |
|
Pose Estimation (HP)
|
100% |
18998
22.2 IPS |
|
Pose Estimation (Q)
|
97% |
44999
52.7 IPS |
|
Object Detection (SP)
|
100% |
182
14.4 IPS |
|
Object Detection (HP)
|
100% |
184
14.6 IPS |
|
Object Detection (Q)
|
87% |
537
43.1 IPS |
|
Face Detection (SP)
|
100% |
447
5.31 IPS |
|
Face Detection (HP)
|
100% |
9671
114.9 IPS |
|
Face Detection (Q)
|
97% |
19155
228.4 IPS |
|
Depth Estimation (SP)
|
100% |
390
3.00 IPS |
|
Depth Estimation (HP)
|
99% |
19213
148.0 IPS |
|
Depth Estimation (Q)
|
64% |
26970
248.3 IPS |
|
Style Transfer (SP)
|
100% |
654
0.84 IPS |
|
Style Transfer (HP)
|
100% |
642
0.83 IPS |
|
Style Transfer (Q)
|
98% |
3126
4.03 IPS |
|
Image Super-Resolution (SP)
|
100% |
195
7.21 IPS |
|
Image Super-Resolution (HP)
|
100% |
194
7.18 IPS |
|
Image Super-Resolution (Q)
|
97% |
10463
387.7 IPS |
|
Text Classification (SP)
|
100% |
290
386.7 IPS |
|
Text Classification (HP)
|
100% |
282
376.5 IPS |
|
Text Classification (Q)
|
92% |
1567
2.11 KIPS |
|
Machine Translation (SP)
|
100% |
444
7.65 IPS |
|
Machine Translation (HP)
|
100% |
424
7.31 IPS |
|
Machine Translation (Q)
|
57% |
290
7.09 IPS |