User | DemonShell |
Upload Date | February 24 2025 10:40 AM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Google Tensor G3 |
System Information | |
---|---|
Operating System | Android 15 |
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% |
314
58.3 IPS |
|
Image Classification (HP)
|
100% |
399
74.2 IPS |
|
Image Classification (Q)
|
99% |
291
54.2 IPS |
|
Image Segmentation (SP)
|
100% |
987
16.0 IPS |
|
Image Segmentation (HP)
|
100% |
1008
16.3 IPS |
|
Image Segmentation (Q)
|
98% |
1040
16.9 IPS |
|
Pose Estimation (SP)
|
100% |
478
0.56 IPS |
|
Pose Estimation (HP)
|
100% |
671
0.78 IPS |
|
Pose Estimation (Q)
|
96% |
662
0.77 IPS |
|
Object Detection (SP)
|
100% |
317
25.1 IPS |
|
Object Detection (HP)
|
100% |
402
31.9 IPS |
|
Object Detection (Q)
|
83% |
425
34.4 IPS |
|
Face Detection (SP)
|
100% |
1196
14.2 IPS |
|
Face Detection (HP)
|
100% |
1433
17.0 IPS |
|
Face Detection (Q)
|
97% |
1243
14.8 IPS |
|
Depth Estimation (SP)
|
100% |
910
7.01 IPS |
|
Depth Estimation (HP)
|
99% |
1126
8.68 IPS |
|
Depth Estimation (Q)
|
62% |
900
8.52 IPS |
|
Style Transfer (SP)
|
100% |
2518
3.24 IPS |
|
Style Transfer (HP)
|
100% |
3327
4.28 IPS |
|
Style Transfer (Q)
|
98% |
3265
4.21 IPS |
|
Image Super-Resolution (SP)
|
100% |
495
18.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
593
21.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
560
20.7 IPS |
|
Text Classification (SP)
|
100% |
267
356.1 IPS |
|
Text Classification (HP)
|
100% |
307
410.1 IPS |
|
Text Classification (Q)
|
91% |
611
821.2 IPS |
|
Machine Translation (SP)
|
100% |
567
9.77 IPS |
|
Machine Translation (HP)
|
100% |
557
9.59 IPS |
|
Machine Translation (Q)
|
57% |
379
9.25 IPS |