User | rgba |
Upload Date | August 15 2024 08:09 PM |
Views | 7 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Google Tensor G3 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Google Pixel 8 |
Model ID | Google Pixel 8 |
Motherboard | shiba |
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% |
1428
265.6 IPS |
|
Image Classification (HP)
|
100% |
985
183.2 IPS |
|
Image Classification (Q)
|
100% |
2351
437.2 IPS |
|
Image Segmentation (SP)
|
100% |
578
9.36 IPS |
|
Image Segmentation (HP)
|
100% |
1683
27.3 IPS |
|
Image Segmentation (Q)
|
98% |
2656
43.2 IPS |
|
Pose Estimation (SP)
|
100% |
2735
3.19 IPS |
|
Pose Estimation (HP)
|
100% |
2657
3.10 IPS |
|
Pose Estimation (Q)
|
84% |
4561
5.41 IPS |
|
Object Detection (SP)
|
98% |
939
74.7 IPS |
|
Object Detection (HP)
|
98% |
1013
80.6 IPS |
|
Object Detection (Q)
|
87% |
1528
122.7 IPS |
|
Face Detection (SP)
|
100% |
2319
27.6 IPS |
|
Face Detection (HP)
|
100% |
2195
26.1 IPS |
|
Face Detection (Q)
|
95% |
1837
21.9 IPS |
|
Depth Estimation (SP)
|
99% |
2113
16.3 IPS |
|
Depth Estimation (HP)
|
99% |
1226
9.48 IPS |
|
Depth Estimation (Q)
|
75% |
3664
29.7 IPS |
|
Style Transfer (SP)
|
89% |
5031
6.53 IPS |
|
Style Transfer (HP)
|
89% |
2833
3.68 IPS |
|
Style Transfer (Q)
|
98% |
4517
5.83 IPS |
|
Image Super-Resolution (SP)
|
100% |
570
21.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
579
21.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
1243
46.1 IPS |
|
Text Classification (SP)
|
100% |
413
550.7 IPS |
|
Text Classification (HP)
|
99% |
247
330.3 IPS |
|
Text Classification (Q)
|
88% |
719
970.3 IPS |
|
Machine Translation (SP)
|
100% |
951
16.4 IPS |
|
Machine Translation (HP)
|
100% |
923
15.9 IPS |
|
Machine Translation (Q)
|
50% |
462
16.4 IPS |