Upload Date | December 28 2024 07:43 AM |
Views | 2 |
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% |
213
39.7 IPS |
|
Image Classification (HP)
|
100% |
4267
793.6 IPS |
|
Image Classification (Q)
|
99% |
6864
1.28 KIPS |
|
Image Segmentation (SP)
|
100% |
275
4.47 IPS |
|
Image Segmentation (HP)
|
100% |
3239
52.5 IPS |
|
Image Segmentation (Q)
|
98% |
9328
151.7 IPS |
|
Pose Estimation (SP)
|
100% |
337
0.39 IPS |
|
Pose Estimation (HP)
|
100% |
19508
22.8 IPS |
|
Pose Estimation (Q)
|
97% |
44514
52.1 IPS |
|
Object Detection (SP)
|
100% |
189
15.0 IPS |
|
Object Detection (HP)
|
100% |
194
15.4 IPS |
|
Object Detection (Q)
|
87% |
547
43.9 IPS |
|
Face Detection (SP)
|
100% |
473
5.62 IPS |
|
Face Detection (HP)
|
100% |
9435
112.1 IPS |
|
Face Detection (Q)
|
97% |
18187
216.9 IPS |
|
Depth Estimation (SP)
|
100% |
408
3.14 IPS |
|
Depth Estimation (HP)
|
99% |
20496
157.9 IPS |
|
Depth Estimation (Q)
|
64% |
25996
239.3 IPS |
|
Style Transfer (SP)
|
100% |
678
0.87 IPS |
|
Style Transfer (HP)
|
100% |
664
0.85 IPS |
|
Style Transfer (Q)
|
98% |
3138
4.05 IPS |
|
Image Super-Resolution (SP)
|
100% |
182
6.74 IPS |
|
Image Super-Resolution (HP)
|
100% |
189
6.97 IPS |
|
Image Super-Resolution (Q)
|
97% |
13446
498.3 IPS |
|
Text Classification (SP)
|
100% |
266
355.6 IPS |
|
Text Classification (HP)
|
100% |
266
355.7 IPS |
|
Text Classification (Q)
|
92% |
1719
2.31 KIPS |
|
Machine Translation (SP)
|
100% |
411
7.07 IPS |
|
Machine Translation (HP)
|
100% |
418
7.21 IPS |
|
Machine Translation (Q)
|
57% |
295
7.20 IPS |