User | M91 |
Upload Date | November 19 2024 01:55 PM |
Views | 4 |
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% |
961
178.7 IPS |
|
Image Classification (HP)
|
100% |
1063
197.7 IPS |
|
Image Classification (Q)
|
100% |
2558
475.7 IPS |
|
Image Segmentation (SP)
|
100% |
1156
18.7 IPS |
|
Image Segmentation (HP)
|
100% |
1172
19.0 IPS |
|
Image Segmentation (Q)
|
98% |
2739
44.5 IPS |
|
Pose Estimation (SP)
|
100% |
2961
3.45 IPS |
|
Pose Estimation (HP)
|
100% |
2903
3.39 IPS |
|
Pose Estimation (Q)
|
84% |
6462
7.66 IPS |
|
Object Detection (SP)
|
98% |
999
79.5 IPS |
|
Object Detection (HP)
|
98% |
977
77.7 IPS |
|
Object Detection (Q)
|
83% |
1394
112.6 IPS |
|
Face Detection (SP)
|
100% |
2292
27.2 IPS |
|
Face Detection (HP)
|
100% |
2308
27.4 IPS |
|
Face Detection (Q)
|
95% |
5637
67.3 IPS |
|
Depth Estimation (SP)
|
99% |
2078
16.1 IPS |
|
Depth Estimation (HP)
|
99% |
2987
23.1 IPS |
|
Depth Estimation (Q)
|
64% |
4940
45.2 IPS |
|
Style Transfer (SP)
|
89% |
6783
8.80 IPS |
|
Style Transfer (HP)
|
89% |
6312
8.19 IPS |
|
Style Transfer (Q)
|
98% |
12162
15.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
1239
45.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
1190
43.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
2450
90.8 IPS |
|
Text Classification (SP)
|
100% |
493
658.5 IPS |
|
Text Classification (HP)
|
99% |
487
650.4 IPS |
|
Text Classification (Q)
|
88% |
784
1.06 KIPS |
|
Machine Translation (SP)
|
100% |
1005
17.3 IPS |
|
Machine Translation (HP)
|
100% |
913
15.7 IPS |
|
Machine Translation (Q)
|
50% |
469
16.6 IPS |