User | noderaser |
Upload Date | December 05 2024 10:07 PM |
Views | 2 |
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% |
236
43.8 IPS |
|
Image Classification (HP)
|
100% |
430
79.9 IPS |
|
Image Classification (Q)
|
99% |
449
83.7 IPS |
|
Image Segmentation (SP)
|
100% |
1009
16.4 IPS |
|
Image Segmentation (HP)
|
100% |
1007
16.3 IPS |
|
Image Segmentation (Q)
|
98% |
1083
17.6 IPS |
|
Pose Estimation (SP)
|
100% |
485
0.57 IPS |
|
Pose Estimation (HP)
|
100% |
692
0.81 IPS |
|
Pose Estimation (Q)
|
96% |
687
0.80 IPS |
|
Object Detection (SP)
|
100% |
288
22.8 IPS |
|
Object Detection (HP)
|
100% |
300
23.8 IPS |
|
Object Detection (Q)
|
83% |
327
26.4 IPS |
|
Face Detection (SP)
|
100% |
1264
15.0 IPS |
|
Face Detection (HP)
|
100% |
1660
19.7 IPS |
|
Face Detection (Q)
|
97% |
1344
16.0 IPS |
|
Depth Estimation (SP)
|
100% |
901
6.94 IPS |
|
Depth Estimation (HP)
|
99% |
1107
8.53 IPS |
|
Depth Estimation (Q)
|
62% |
877
8.30 IPS |
|
Style Transfer (SP)
|
100% |
2514
3.23 IPS |
|
Style Transfer (HP)
|
100% |
3234
4.16 IPS |
|
Style Transfer (Q)
|
98% |
3236
4.17 IPS |
|
Image Super-Resolution (SP)
|
100% |
468
17.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
540
19.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
520
19.3 IPS |
|
Text Classification (SP)
|
100% |
290
386.6 IPS |
|
Text Classification (HP)
|
100% |
355
473.2 IPS |
|
Text Classification (Q)
|
91% |
612
823.1 IPS |
|
Machine Translation (SP)
|
100% |
557
9.59 IPS |
|
Machine Translation (HP)
|
100% |
551
9.49 IPS |
|
Machine Translation (Q)
|
57% |
348
8.51 IPS |