User | M91 |
Upload Date | November 20 2024 12:25 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Google Pixel 8a |
Model ID | Google Pixel 8a |
Motherboard | akita |
Governor | sched_pixel |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 9 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
Base Frequency | 1.70 GHz |
Cluster 1 | 4 Cores @ 1.70 GHz |
Cluster 2 | 4 Cores @ 2.37 GHz |
Cluster 3 | 1 Core @ 2.91 GHz |
Memory Information | |
---|---|
Size | 7.42 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
959
178.4 IPS |
|
Image Classification (HP)
|
100% |
1051
195.4 IPS |
|
Image Classification (Q)
|
100% |
2337
434.6 IPS |
|
Image Segmentation (SP)
|
100% |
1145
18.6 IPS |
|
Image Segmentation (HP)
|
100% |
1701
27.6 IPS |
|
Image Segmentation (Q)
|
98% |
2465
40.1 IPS |
|
Pose Estimation (SP)
|
100% |
2621
3.06 IPS |
|
Pose Estimation (HP)
|
100% |
2337
2.73 IPS |
|
Pose Estimation (Q)
|
84% |
4744
5.63 IPS |
|
Object Detection (SP)
|
98% |
1014
80.7 IPS |
|
Object Detection (HP)
|
98% |
996
79.3 IPS |
|
Object Detection (Q)
|
83% |
1479
119.5 IPS |
|
Face Detection (SP)
|
100% |
2219
26.4 IPS |
|
Face Detection (HP)
|
100% |
2214
26.3 IPS |
|
Face Detection (Q)
|
95% |
3383
40.4 IPS |
|
Depth Estimation (SP)
|
99% |
2048
15.8 IPS |
|
Depth Estimation (HP)
|
99% |
2071
16.0 IPS |
|
Depth Estimation (Q)
|
64% |
3435
31.5 IPS |
|
Style Transfer (SP)
|
89% |
5041
6.54 IPS |
|
Style Transfer (HP)
|
89% |
5003
6.49 IPS |
|
Style Transfer (Q)
|
98% |
9633
12.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
1049
38.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
1047
38.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
2405
89.1 IPS |
|
Text Classification (SP)
|
100% |
453
605.2 IPS |
|
Text Classification (HP)
|
99% |
452
603.1 IPS |
|
Text Classification (Q)
|
88% |
745
1.00 KIPS |
|
Machine Translation (SP)
|
100% |
988
17.0 IPS |
|
Machine Translation (HP)
|
100% |
959
16.5 IPS |
|
Machine Translation (Q)
|
50% |
468
16.6 IPS |