User | M91 |
Upload Date | August 26 2024 03:53 AM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
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% |
363
67.5 IPS |
|
Image Classification (HP)
|
100% |
405
75.3 IPS |
|
Image Classification (Q)
|
97% |
329
61.5 IPS |
|
Image Segmentation (SP)
|
100% |
846
13.7 IPS |
|
Image Segmentation (HP)
|
100% |
978
15.9 IPS |
|
Image Segmentation (Q)
|
98% |
880
14.3 IPS |
|
Pose Estimation (SP)
|
100% |
478
0.56 IPS |
|
Pose Estimation (HP)
|
100% |
666
0.78 IPS |
|
Pose Estimation (Q)
|
96% |
662
0.78 IPS |
|
Object Detection (SP)
|
100% |
275
21.9 IPS |
|
Object Detection (HP)
|
100% |
316
25.1 IPS |
|
Object Detection (Q)
|
92% |
330
26.4 IPS |
|
Face Detection (SP)
|
100% |
1185
14.1 IPS |
|
Face Detection (HP)
|
100% |
1205
14.3 IPS |
|
Face Detection (Q)
|
97% |
1153
13.8 IPS |
|
Depth Estimation (SP)
|
100% |
913
7.03 IPS |
|
Depth Estimation (HP)
|
99% |
1112
8.57 IPS |
|
Depth Estimation (Q)
|
72% |
1013
8.39 IPS |
|
Style Transfer (SP)
|
100% |
2463
3.17 IPS |
|
Style Transfer (HP)
|
100% |
3303
4.25 IPS |
|
Style Transfer (Q)
|
98% |
3290
4.24 IPS |
|
Image Super-Resolution (SP)
|
100% |
479
17.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
553
20.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
557
20.6 IPS |
|
Text Classification (SP)
|
100% |
129
172.2 IPS |
|
Text Classification (HP)
|
100% |
130
173.7 IPS |
|
Text Classification (Q)
|
91% |
249
335.1 IPS |
|
Machine Translation (SP)
|
100% |
225
3.88 IPS |
|
Machine Translation (HP)
|
100% |
216
3.72 IPS |
|
Machine Translation (Q)
|
57% |
144
3.53 IPS |