User | aeonsim |
Upload Date | September 08 2024 08:45 AM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Google Tensor G2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Google Pixel 7 |
Model ID | Google Pixel 7 |
Motherboard | panther |
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 | 7.30 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
242
45.0 IPS |
|
Image Classification (HP)
|
100% |
246
45.8 IPS |
|
Image Classification (Q)
|
99% |
256
47.8 IPS |
|
Image Segmentation (SP)
|
100% |
649
10.5 IPS |
|
Image Segmentation (HP)
|
100% |
819
13.3 IPS |
|
Image Segmentation (Q)
|
98% |
821
13.3 IPS |
|
Pose Estimation (SP)
|
100% |
453
0.53 IPS |
|
Pose Estimation (HP)
|
100% |
622
0.73 IPS |
|
Pose Estimation (Q)
|
96% |
618
0.72 IPS |
|
Object Detection (SP)
|
100% |
216
17.1 IPS |
|
Object Detection (HP)
|
100% |
291
23.1 IPS |
|
Object Detection (Q)
|
83% |
289
23.4 IPS |
|
Face Detection (SP)
|
100% |
1065
12.7 IPS |
|
Face Detection (HP)
|
100% |
1310
15.6 IPS |
|
Face Detection (Q)
|
97% |
1203
14.3 IPS |
|
Depth Estimation (SP)
|
100% |
758
5.84 IPS |
|
Depth Estimation (HP)
|
99% |
915
7.05 IPS |
|
Depth Estimation (Q)
|
62% |
736
6.97 IPS |
|
Style Transfer (SP)
|
100% |
2005
2.58 IPS |
|
Style Transfer (HP)
|
100% |
2574
3.31 IPS |
|
Style Transfer (Q)
|
98% |
2560
3.30 IPS |
|
Image Super-Resolution (SP)
|
100% |
358
13.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
445
16.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
449
16.6 IPS |
|
Text Classification (SP)
|
100% |
327
437.0 IPS |
|
Text Classification (HP)
|
100% |
327
437.1 IPS |
|
Text Classification (Q)
|
91% |
537
722.4 IPS |
|
Machine Translation (SP)
|
100% |
487
8.38 IPS |
|
Machine Translation (HP)
|
100% |
475
8.17 IPS |
|
Machine Translation (Q)
|
57% |
316
7.73 IPS |