Upload Date | July 12 2025 03:51 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Google Tensor G2 |
System Information | |
---|---|
Operating System | Android 16 |
Model | Google Pixel 7a |
Model ID | Google Pixel 7a |
Motherboard | lynx |
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 @ 2.35 GHz |
Cluster 3 | 2 Cores @ 2.85 GHz |
Memory Information | |
---|---|
Size | 7.27 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
139
25.8 IPS |
|
Image Classification (HP)
|
100% |
5584
1.04 KIPS |
|
Image Classification (Q)
|
99% |
8580
1.60 KIPS |
|
Image Segmentation (SP)
|
100% |
171
2.78 IPS |
|
Image Segmentation (HP)
|
100% |
5435
88.1 IPS |
|
Image Segmentation (Q)
|
98% |
9549
155.3 IPS |
|
Pose Estimation (SP)
|
100% |
205
0.24 IPS |
|
Pose Estimation (HP)
|
100% |
16604
19.4 IPS |
|
Pose Estimation (Q)
|
97% |
30344
35.5 IPS |
|
Object Detection (SP)
|
100% |
113
8.94 IPS |
|
Object Detection (HP)
|
100% |
3843
304.8 IPS |
|
Object Detection (Q)
|
87% |
5447
437.0 IPS |
|
Face Detection (SP)
|
100% |
305
3.63 IPS |
|
Face Detection (HP)
|
100% |
308
3.66 IPS |
|
Face Detection (Q)
|
97% |
24872
296.6 IPS |
|
Depth Estimation (SP)
|
100% |
221
1.71 IPS |
|
Depth Estimation (HP)
|
99% |
18355
141.4 IPS |
|
Depth Estimation (Q)
|
64% |
26574
244.6 IPS |
|
Style Transfer (SP)
|
100% |
322
0.41 IPS |
|
Style Transfer (HP)
|
100% |
322
0.41 IPS |
|
Style Transfer (Q)
|
58% |
1526
2.74 IPS |
|
Image Super-Resolution (SP)
|
100% |
100
3.68 IPS |
|
Image Super-Resolution (HP)
|
100% |
5092
188.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
11131
412.5 IPS |
|
Text Classification (SP)
|
100% |
143
190.4 IPS |
|
Text Classification (HP)
|
100% |
159
212.5 IPS |
|
Text Classification (Q)
|
92% |
2104
2.83 KIPS |
|
Machine Translation (SP)
|
100% |
253
4.35 IPS |
|
Machine Translation (HP)
|
100% |
238
4.10 IPS |
|
Machine Translation (Q)
|
57% |
246
6.01 IPS |