User | timk |
Upload Date | August 23 2024 08:48 PM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Google Tensor G2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Google Pixel 7 Pro |
Model ID | Google Pixel 7 Pro |
Motherboard | cheetah |
Governor | sched_pixel |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.35 GHz |
Cluster 3 | 2 Cores @ 2.85 GHz |
Memory Information | |
---|---|
Size | 11.20 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
263
48.9 IPS |
|
Image Classification (HP)
|
100% |
232
43.1 IPS |
|
Image Classification (Q)
|
97% |
234
43.7 IPS |
|
Image Segmentation (SP)
|
100% |
623
10.1 IPS |
|
Image Segmentation (HP)
|
100% |
845
13.7 IPS |
|
Image Segmentation (Q)
|
98% |
790
12.8 IPS |
|
Pose Estimation (SP)
|
100% |
453
0.53 IPS |
|
Pose Estimation (HP)
|
100% |
622
0.73 IPS |
|
Pose Estimation (Q)
|
96% |
616
0.72 IPS |
|
Object Detection (SP)
|
100% |
235
18.6 IPS |
|
Object Detection (HP)
|
100% |
293
23.3 IPS |
|
Object Detection (Q)
|
92% |
284
22.7 IPS |
|
Face Detection (SP)
|
100% |
1103
13.1 IPS |
|
Face Detection (HP)
|
100% |
1163
13.8 IPS |
|
Face Detection (Q)
|
97% |
1152
13.7 IPS |
|
Depth Estimation (SP)
|
100% |
766
5.90 IPS |
|
Depth Estimation (HP)
|
99% |
906
6.98 IPS |
|
Depth Estimation (Q)
|
72% |
842
6.97 IPS |
|
Style Transfer (SP)
|
100% |
2013
2.59 IPS |
|
Style Transfer (HP)
|
100% |
2545
3.27 IPS |
|
Style Transfer (Q)
|
98% |
2496
3.22 IPS |
|
Image Super-Resolution (SP)
|
100% |
363
13.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
465
17.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
457
16.9 IPS |
|
Text Classification (SP)
|
100% |
302
403.6 IPS |
|
Text Classification (HP)
|
100% |
302
402.7 IPS |
|
Text Classification (Q)
|
91% |
519
697.8 IPS |
|
Machine Translation (SP)
|
100% |
448
7.71 IPS |
|
Machine Translation (HP)
|
100% |
430
7.41 IPS |
|
Machine Translation (Q)
|
57% |
278
6.79 IPS |