User | M91 |
Upload Date | September 24 2025 05:43 PM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 16 |
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 | 7.38 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
397
73.9 IPS |
|
Image Classification (HP)
|
100% |
453
84.3 IPS |
|
Image Classification (Q)
|
97% |
394
73.5 IPS |
|
Image Segmentation (SP)
|
100% |
1330
21.6 IPS |
|
Image Segmentation (HP)
|
100% |
1968
31.9 IPS |
|
Image Segmentation (Q)
|
98% |
1798
29.2 IPS |
|
Pose Estimation (SP)
|
100% |
4877
5.69 IPS |
|
Pose Estimation (HP)
|
100% |
11998
14.0 IPS |
|
Pose Estimation (Q)
|
95% |
11717
13.7 IPS |
|
Object Detection (SP)
|
100% |
596
47.3 IPS |
|
Object Detection (HP)
|
99% |
887
70.4 IPS |
|
Object Detection (Q)
|
83% |
825
66.6 IPS |
|
Face Detection (SP)
|
100% |
2077
24.7 IPS |
|
Face Detection (HP)
|
100% |
3073
36.5 IPS |
|
Face Detection (Q)
|
96% |
2449
29.2 IPS |
|
Depth Estimation (SP)
|
100% |
3297
25.4 IPS |
|
Depth Estimation (HP)
|
98% |
5619
43.4 IPS |
|
Depth Estimation (Q)
|
62% |
4341
41.2 IPS |
|
Style Transfer (SP)
|
100% |
7470
9.60 IPS |
|
Style Transfer (HP)
|
100% |
19600
25.2 IPS |
|
Style Transfer (Q)
|
98% |
18475
23.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
1714
63.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
2149
79.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
2035
75.4 IPS |
|
Text Classification (SP)
|
35% |
16
142.7 IPS |
|
Text Classification (HP)
|
35% |
17
158.1 IPS |
|
Text Classification (Q)
|
32% |
12
150.3 IPS |
|
Machine Translation (SP)
|
100% |
242
4.17 IPS |
|
Machine Translation (HP)
|
100% |
275
4.73 IPS |
|
Machine Translation (Q)
|
43% |
72
4.20 IPS |