Upload Date | August 22 2024 11:13 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Google Tensor |
System Information | |
---|---|
Operating System | Android 14 |
Model | Google Pixel 6a |
Model ID | Google Pixel 6a |
Motherboard | bluejay |
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 @ 2.25 GHz |
Cluster 3 | 2 Cores @ 2.80 GHz |
Memory Information | |
---|---|
Size | 5.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
207
38.4 IPS |
|
Image Classification (HP)
|
100% |
4376
813.8 IPS |
|
Image Classification (Q)
|
99% |
7508
1.40 KIPS |
|
Image Segmentation (SP)
|
100% |
256
4.15 IPS |
|
Image Segmentation (HP)
|
100% |
3410
55.3 IPS |
|
Image Segmentation (Q)
|
98% |
2076
33.8 IPS |
|
Pose Estimation (SP)
|
100% |
322
0.38 IPS |
|
Pose Estimation (HP)
|
100% |
18808
21.9 IPS |
|
Pose Estimation (Q)
|
97% |
43429
50.9 IPS |
|
Object Detection (SP)
|
100% |
174
13.8 IPS |
|
Object Detection (HP)
|
100% |
170
13.5 IPS |
|
Object Detection (Q)
|
89% |
527
42.2 IPS |
|
Face Detection (SP)
|
100% |
446
5.30 IPS |
|
Face Detection (HP)
|
100% |
9652
114.7 IPS |
|
Face Detection (Q)
|
97% |
18679
222.7 IPS |
|
Depth Estimation (SP)
|
100% |
368
2.83 IPS |
|
Depth Estimation (HP)
|
99% |
19095
147.1 IPS |
|
Depth Estimation (Q)
|
70% |
29653
249.8 IPS |
|
Style Transfer (SP)
|
100% |
630
0.81 IPS |
|
Style Transfer (HP)
|
100% |
633
0.81 IPS |
|
Style Transfer (Q)
|
98% |
3068
3.96 IPS |
|
Image Super-Resolution (SP)
|
100% |
181
6.69 IPS |
|
Image Super-Resolution (HP)
|
100% |
184
6.81 IPS |
|
Image Super-Resolution (Q)
|
97% |
11434
423.7 IPS |
|
Text Classification (SP)
|
100% |
271
361.8 IPS |
|
Text Classification (HP)
|
100% |
282
376.2 IPS |
|
Text Classification (Q)
|
92% |
1601
2.15 KIPS |
|
Machine Translation (SP)
|
100% |
416
7.17 IPS |
|
Machine Translation (HP)
|
100% |
400
6.89 IPS |
|
Machine Translation (Q)
|
57% |
280
6.85 IPS |