User | M91 |
Upload Date | October 15 2024 10:54 AM |
Views | 2 |
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% |
368
68.5 IPS |
|
Image Classification (HP)
|
100% |
393
73.1 IPS |
|
Image Classification (Q)
|
99% |
324
60.5 IPS |
|
Image Segmentation (SP)
|
100% |
875
14.2 IPS |
|
Image Segmentation (HP)
|
100% |
996
16.1 IPS |
|
Image Segmentation (Q)
|
98% |
934
15.2 IPS |
|
Pose Estimation (SP)
|
100% |
478
0.56 IPS |
|
Pose Estimation (HP)
|
100% |
666
0.78 IPS |
|
Pose Estimation (Q)
|
96% |
663
0.78 IPS |
|
Object Detection (SP)
|
100% |
251
19.9 IPS |
|
Object Detection (HP)
|
100% |
295
23.4 IPS |
|
Object Detection (Q)
|
83% |
363
29.4 IPS |
|
Face Detection (SP)
|
100% |
1159
13.8 IPS |
|
Face Detection (HP)
|
100% |
1341
15.9 IPS |
|
Face Detection (Q)
|
97% |
1267
15.1 IPS |
|
Depth Estimation (SP)
|
100% |
906
6.98 IPS |
|
Depth Estimation (HP)
|
99% |
1089
8.39 IPS |
|
Depth Estimation (Q)
|
62% |
879
8.32 IPS |
|
Style Transfer (SP)
|
100% |
2463
3.17 IPS |
|
Style Transfer (HP)
|
100% |
3216
4.13 IPS |
|
Style Transfer (Q)
|
98% |
3222
4.15 IPS |
|
Image Super-Resolution (SP)
|
100% |
444
16.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
516
19.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
505
18.7 IPS |
|
Text Classification (SP)
|
100% |
380
507.1 IPS |
|
Text Classification (HP)
|
100% |
374
498.7 IPS |
|
Text Classification (Q)
|
91% |
573
769.7 IPS |
|
Machine Translation (SP)
|
100% |
536
9.24 IPS |
|
Machine Translation (HP)
|
100% |
527
9.08 IPS |
|
Machine Translation (Q)
|
57% |
355
8.67 IPS |