User | dipak |
Upload Date | December 04 2024 01:38 AM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Google Tensor G4 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Google Pixel 9 Pro |
Model ID | Google Pixel 9 Pro |
Motherboard | caiman |
Governor | sched_pixel |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3458 revision 1 |
Base Frequency | 1.95 GHz |
Cluster 1 | 4 Cores @ 1.95 GHz |
Cluster 2 | 3 Cores @ 2.60 GHz |
Cluster 3 | 1 Core @ 3.10 GHz |
Memory Information | |
---|---|
Size | 15.19 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
537
99.8 IPS |
|
Image Classification (HP)
|
100% |
475
88.4 IPS |
|
Image Classification (Q)
|
99% |
447
83.4 IPS |
|
Image Segmentation (SP)
|
100% |
949
15.4 IPS |
|
Image Segmentation (HP)
|
100% |
1017
16.5 IPS |
|
Image Segmentation (Q)
|
98% |
990
16.1 IPS |
|
Pose Estimation (SP)
|
100% |
516
0.60 IPS |
|
Pose Estimation (HP)
|
100% |
734
0.86 IPS |
|
Pose Estimation (Q)
|
96% |
728
0.85 IPS |
|
Object Detection (SP)
|
100% |
339
26.9 IPS |
|
Object Detection (HP)
|
100% |
407
32.3 IPS |
|
Object Detection (Q)
|
83% |
430
34.8 IPS |
|
Face Detection (SP)
|
100% |
1456
17.3 IPS |
|
Face Detection (HP)
|
100% |
1631
19.4 IPS |
|
Face Detection (Q)
|
97% |
1380
16.5 IPS |
|
Depth Estimation (SP)
|
100% |
978
7.54 IPS |
|
Depth Estimation (HP)
|
99% |
1202
9.26 IPS |
|
Depth Estimation (Q)
|
62% |
967
9.16 IPS |
|
Style Transfer (SP)
|
100% |
2700
3.47 IPS |
|
Style Transfer (HP)
|
100% |
3546
4.56 IPS |
|
Style Transfer (Q)
|
98% |
3484
4.49 IPS |
|
Image Super-Resolution (SP)
|
100% |
545
20.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
611
22.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
590
21.9 IPS |
|
Text Classification (SP)
|
100% |
421
562.6 IPS |
|
Text Classification (HP)
|
100% |
421
561.8 IPS |
|
Text Classification (Q)
|
91% |
692
929.8 IPS |
|
Machine Translation (SP)
|
100% |
572
9.86 IPS |
|
Machine Translation (HP)
|
100% |
544
9.37 IPS |
|
Machine Translation (Q)
|
57% |
371
9.07 IPS |