| User | aeonsim |
| Upload Date | August 16 2024 03:33 AM |
| Views | 14 |
| 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% |
229
42.7 IPS |
|
|
Image Classification (HP)
|
100% |
251
46.7 IPS |
|
|
Image Classification (Q)
|
97% |
236
44.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
623
10.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
809
13.1 IPS |
|
|
Image Segmentation (Q)
|
98% |
789
12.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
454
0.53 IPS |
|
|
Pose Estimation (HP)
|
100% |
621
0.72 IPS |
|
|
Pose Estimation (Q)
|
96% |
618
0.72 IPS |
|
|
Object Detection (SP)
|
100% |
241
19.1 IPS |
|
|
Object Detection (HP)
|
100% |
311
24.7 IPS |
|
|
Object Detection (Q)
|
92% |
287
22.9 IPS |
|
|
Face Detection (SP)
|
100% |
1028
12.2 IPS |
|
|
Face Detection (HP)
|
100% |
1215
14.4 IPS |
|
|
Face Detection (Q)
|
97% |
1193
14.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
760
5.86 IPS |
|
|
Depth Estimation (HP)
|
99% |
925
7.13 IPS |
|
|
Depth Estimation (Q)
|
72% |
846
7.00 IPS |
|
|
Style Transfer (SP)
|
100% |
2028
2.61 IPS |
|
|
Style Transfer (HP)
|
100% |
2614
3.36 IPS |
|
|
Style Transfer (Q)
|
98% |
2565
3.31 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
369
13.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
471
17.4 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
448
16.6 IPS |
|
|
Text Classification (SP)
|
100% |
325
433.5 IPS |
|
|
Text Classification (HP)
|
100% |
326
434.9 IPS |
|
|
Text Classification (Q)
|
91% |
539
724.2 IPS |
|
|
Machine Translation (SP)
|
100% |
476
8.20 IPS |
|
|
Machine Translation (HP)
|
100% |
470
8.09 IPS |
|
|
Machine Translation (Q)
|
57% |
296
7.23 IPS |