Upload Date | January 23 2024 09:22 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
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 |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
246
46.0 IPS |
|
Image Classification (F16)
|
100% |
431
80.7 IPS |
|
Image Classification (I8)
|
97% |
416
77.8 IPS |
|
Image Segmentation (F32)
|
100% |
633
10.6 IPS |
|
Image Segmentation (F16)
|
100% |
996
16.6 IPS |
|
Image Segmentation (I8)
|
98% |
934
15.6 IPS |
|
Pose Estimation (F32)
|
100% |
327
0.40 IPS |
|
Pose Estimation (F16)
|
100% |
426
0.52 IPS |
|
Pose Estimation (I8)
|
100% |
424
0.51 IPS |
|
Object Detection (F32)
|
100% |
296
22.1 IPS |
|
Object Detection (F16)
|
100% |
346
25.9 IPS |
|
Object Detection (I8)
|
62% |
276
20.6 IPS |
|
Face Detection (F32)
|
100% |
1289
15.3 IPS |
|
Face Detection (F16)
|
98% |
1664
19.8 IPS |
|
Face Detection (I8)
|
86% |
1705
20.3 IPS |
|
Depth Estimation (F32)
|
100% |
620
4.81 IPS |
|
Depth Estimation (F16)
|
100% |
725
5.62 IPS |
|
Depth Estimation (I8)
|
95% |
709
5.50 IPS |
|
Style Transfer (F32)
|
100% |
1384
1.82 IPS |
|
Style Transfer (F16)
|
100% |
2537
3.34 IPS |
|
Style Transfer (I8)
|
98% |
2537
3.34 IPS |
|
Image Super-Resolution (F32)
|
100% |
444
15.9 IPS |
|
Image Super-Resolution (F16)
|
100% |
651
23.3 IPS |
|
Image Super-Resolution (I8)
|
98% |
654
23.3 IPS |
|
Text Classification (F32)
|
100% |
262
375.8 IPS |
|
Text Classification (F16)
|
100% |
277
398.7 IPS |
|
Text Classification (I8)
|
92% |
487
699.2 IPS |
|
Machine Translation (F32)
|
100% |
410
7.54 IPS |
|
Machine Translation (F16)
|
100% |
406
7.47 IPS |
|
Machine Translation (I8)
|
64% |
421
7.75 IPS |