User | mkacer |
Upload Date | July 03 2025 04:14 PM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Google Tensor G3 |
System Information | |
---|---|
Operating System | Android 16 |
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 | 7.14 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
470
87.4 IPS |
|
Image Classification (HP)
|
100% |
436
81.1 IPS |
|
Image Classification (Q)
|
97% |
341
63.6 IPS |
|
Image Segmentation (SP)
|
100% |
1284
20.8 IPS |
|
Image Segmentation (HP)
|
100% |
1807
29.3 IPS |
|
Image Segmentation (Q)
|
98% |
1586
25.8 IPS |
|
Pose Estimation (SP)
|
100% |
4899
5.72 IPS |
|
Pose Estimation (HP)
|
100% |
12294
14.3 IPS |
|
Pose Estimation (Q)
|
95% |
11990
14.1 IPS |
|
Object Detection (SP)
|
100% |
486
38.5 IPS |
|
Object Detection (HP)
|
99% |
543
43.1 IPS |
|
Object Detection (Q)
|
83% |
623
50.3 IPS |
|
Face Detection (SP)
|
100% |
2087
24.8 IPS |
|
Face Detection (HP)
|
100% |
2427
28.8 IPS |
|
Face Detection (Q)
|
96% |
2138
25.5 IPS |
|
Depth Estimation (SP)
|
100% |
3272
25.2 IPS |
|
Depth Estimation (HP)
|
98% |
5471
42.3 IPS |
|
Depth Estimation (Q)
|
62% |
4450
42.3 IPS |
|
Style Transfer (SP)
|
100% |
7451
9.58 IPS |
|
Style Transfer (HP)
|
100% |
19708
25.3 IPS |
|
Style Transfer (Q)
|
98% |
18249
23.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
1669
61.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
2192
80.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
2002
74.2 IPS |
|
Text Classification (SP)
|
35% |
15
136.8 IPS |
|
Text Classification (HP)
|
35% |
20
181.6 IPS |
|
Text Classification (Q)
|
32% |
11
138.1 IPS |
|
Machine Translation (SP)
|
100% |
233
4.02 IPS |
|
Machine Translation (HP)
|
100% |
275
4.73 IPS |
|
Machine Translation (Q)
|
43% |
67
3.90 IPS |