Upload Date | December 08 2023 02:34 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Google Pixel 5 |
Model ID | Google Pixel 5 |
Motherboard | redfin |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 15 part 2052 revision 14 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 1 Core @ 2.21 GHz |
Cluster 3 | 1 Core @ 2.40 GHz |
Memory Information | |
---|---|
Size | 7.29 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
175
32.8 IPS |
|
Image Classification (F16)
|
99% |
247
46.2 IPS |
|
Image Classification (I8)
|
97% |
809
151.4 IPS |
|
Image Segmentation (F32)
|
100% |
232
3.87 IPS |
|
Image Segmentation (F16)
|
100% |
306
5.12 IPS |
|
Image Segmentation (I8)
|
98% |
851
14.2 IPS |
|
Pose Estimation (F32)
|
100% |
500
0.61 IPS |
|
Pose Estimation (F16)
|
100% |
1246
1.51 IPS |
|
Pose Estimation (I8)
|
100% |
6504
7.88 IPS |
|
Object Detection (F32)
|
100% |
64
4.78 IPS |
|
Object Detection (F16)
|
100% |
71
5.28 IPS |
|
Object Detection (I8)
|
59% |
87
6.51 IPS |
|
Face Detection (F32)
|
100% |
439
5.21 IPS |
|
Face Detection (F16)
|
97% |
532
6.33 IPS |
|
Face Detection (I8)
|
88% |
2375
28.2 IPS |
|
Depth Estimation (F32)
|
100% |
327
2.53 IPS |
|
Depth Estimation (F16)
|
100% |
392
3.04 IPS |
|
Depth Estimation (I8)
|
95% |
4649
36.1 IPS |
|
Style Transfer (F32)
|
100% |
521
0.69 IPS |
|
Style Transfer (F16)
|
100% |
570
0.75 IPS |
|
Style Transfer (I8)
|
98% |
2630
3.46 IPS |
|
Image Super-Resolution (F32)
|
100% |
306
10.9 IPS |
|
Image Super-Resolution (F16)
|
100% |
584
20.9 IPS |
|
Image Super-Resolution (I8)
|
98% |
2978
106.3 IPS |
|
Text Classification (F32)
|
64% |
3
4.12 IPS |
|
Text Classification (F16)
|
64% |
3
4.04 IPS |
|
Text Classification (I8)
|
94% |
94
135.6 IPS |
|
Machine Translation (F32)
|
100% |
112
2.06 IPS |
|
Machine Translation (F16)
|
100% |
285
5.24 IPS |
|
Machine Translation (I8)
|
58% |
218
4.02 IPS |