User | aapivone |
Upload Date | January 04 2025 12:04 AM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Google Tensor |
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 |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
455
84.6 IPS |
|
Image Classification (HP)
|
100% |
417
77.6 IPS |
|
Image Classification (Q)
|
100% |
1195
222.3 IPS |
|
Image Segmentation (SP)
|
100% |
529
8.57 IPS |
|
Image Segmentation (HP)
|
100% |
545
8.83 IPS |
|
Image Segmentation (Q)
|
98% |
1455
23.7 IPS |
|
Pose Estimation (SP)
|
100% |
1991
2.32 IPS |
|
Pose Estimation (HP)
|
100% |
1939
2.26 IPS |
|
Pose Estimation (Q)
|
84% |
2858
3.39 IPS |
|
Object Detection (SP)
|
100% |
423
33.5 IPS |
|
Object Detection (HP)
|
100% |
423
33.5 IPS |
|
Object Detection (Q)
|
83% |
1147
92.7 IPS |
|
Face Detection (SP)
|
100% |
1327
15.8 IPS |
|
Face Detection (HP)
|
100% |
1354
16.1 IPS |
|
Face Detection (Q)
|
95% |
2713
32.4 IPS |
|
Depth Estimation (SP)
|
100% |
1732
13.3 IPS |
|
Depth Estimation (HP)
|
99% |
1706
13.1 IPS |
|
Depth Estimation (Q)
|
64% |
2586
23.7 IPS |
|
Style Transfer (SP)
|
89% |
3074
3.99 IPS |
|
Style Transfer (HP)
|
89% |
3087
4.01 IPS |
|
Style Transfer (Q)
|
98% |
6452
8.32 IPS |
|
Image Super-Resolution (SP)
|
100% |
976
36.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
996
36.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
1636
60.6 IPS |
|
Text Classification (SP)
|
100% |
559
746.5 IPS |
|
Text Classification (HP)
|
100% |
578
771.6 IPS |
|
Text Classification (Q)
|
88% |
1043
1.41 KIPS |
|
Machine Translation (SP)
|
100% |
809
13.9 IPS |
|
Machine Translation (HP)
|
100% |
785
13.5 IPS |
|
Machine Translation (Q)
|
50% |
582
20.6 IPS |