Upload Date | September 11 2024 10:05 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Google Tensor G2 |
System Information | |
---|---|
Operating System | Android 14 |
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 | 7.30 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
229
42.5 IPS |
|
Image Classification (HP)
|
100% |
234
43.5 IPS |
|
Image Classification (Q)
|
99% |
222
41.5 IPS |
|
Image Segmentation (SP)
|
100% |
621
10.1 IPS |
|
Image Segmentation (HP)
|
100% |
848
13.7 IPS |
|
Image Segmentation (Q)
|
98% |
748
12.2 IPS |
|
Pose Estimation (SP)
|
100% |
453
0.53 IPS |
|
Pose Estimation (HP)
|
100% |
622
0.73 IPS |
|
Pose Estimation (Q)
|
96% |
619
0.73 IPS |
|
Object Detection (SP)
|
100% |
247
19.6 IPS |
|
Object Detection (HP)
|
100% |
283
22.4 IPS |
|
Object Detection (Q)
|
83% |
304
24.6 IPS |
|
Face Detection (SP)
|
100% |
1024
12.2 IPS |
|
Face Detection (HP)
|
100% |
1241
14.7 IPS |
|
Face Detection (Q)
|
97% |
1142
13.6 IPS |
|
Depth Estimation (SP)
|
100% |
758
5.84 IPS |
|
Depth Estimation (HP)
|
99% |
917
7.07 IPS |
|
Depth Estimation (Q)
|
62% |
744
7.04 IPS |
|
Style Transfer (SP)
|
100% |
2005
2.58 IPS |
|
Style Transfer (HP)
|
100% |
2571
3.31 IPS |
|
Style Transfer (Q)
|
98% |
2578
3.32 IPS |
|
Image Super-Resolution (SP)
|
100% |
359
13.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
448
16.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
437
16.2 IPS |
|
Text Classification (SP)
|
100% |
298
397.7 IPS |
|
Text Classification (HP)
|
100% |
294
393.0 IPS |
|
Text Classification (Q)
|
91% |
506
680.2 IPS |
|
Machine Translation (SP)
|
100% |
447
7.70 IPS |
|
Machine Translation (HP)
|
100% |
426
7.33 IPS |
|
Machine Translation (Q)
|
57% |
311
7.60 IPS |