Upload Date | July 26 2024 02:36 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | OnePlus PJA110 |
Model ID | OnePlus PJA110 |
Motherboard | kalama |
Governor | uag |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
Base Frequency | 2.02 GHz |
Cluster 1 | 3 Cores @ 2.02 GHz |
Cluster 2 | 4 Cores @ 2.80 GHz |
Cluster 3 | 1 Core @ 3.19 GHz |
Memory Information | |
---|---|
Size | 22.63 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
636
119.1 IPS |
|
Image Classification (F16)
|
100% |
1073
200.8 IPS |
|
Image Classification (I8)
|
99% |
822
153.8 IPS |
|
Image Segmentation (F32)
|
100% |
872
14.6 IPS |
|
Image Segmentation (F16)
|
100% |
973
16.2 IPS |
|
Image Segmentation (I8)
|
98% |
968
16.2 IPS |
|
Pose Estimation (F32)
|
100% |
929
1.13 IPS |
|
Pose Estimation (F16)
|
100% |
1390
1.68 IPS |
|
Pose Estimation (I8)
|
100% |
1387
1.68 IPS |
|
Object Detection (F32)
|
100% |
401
29.9 IPS |
|
Object Detection (F16)
|
100% |
461
34.4 IPS |
|
Object Detection (I8)
|
62% |
573
42.8 IPS |
|
Face Detection (F32)
|
100% |
2254
26.8 IPS |
|
Face Detection (F16)
|
97% |
3298
39.2 IPS |
|
Face Detection (I8)
|
86% |
3149
37.4 IPS |
|
Depth Estimation (F32)
|
100% |
1444
11.2 IPS |
|
Depth Estimation (F16)
|
100% |
2790
21.6 IPS |
|
Depth Estimation (I8)
|
95% |
2755
21.4 IPS |
|
Style Transfer (F32)
|
100% |
3594
4.73 IPS |
|
Style Transfer (F16)
|
100% |
8152
10.7 IPS |
|
Style Transfer (I8)
|
98% |
6327
8.32 IPS |
|
Image Super-Resolution (F32)
|
100% |
460
16.4 IPS |
|
Image Super-Resolution (F16)
|
100% |
416
14.9 IPS |
|
Image Super-Resolution (I8)
|
98% |
421
15.0 IPS |
|
Text Classification (F32)
|
100% |
392
562.8 IPS |
|
Text Classification (F16)
|
100% |
398
571.9 IPS |
|
Text Classification (I8)
|
92% |
576
828.0 IPS |
|
Machine Translation (F32)
|
100% |
588
10.8 IPS |
|
Machine Translation (F16)
|
100% |
588
10.8 IPS |
|
Machine Translation (I8)
|
64% |
582
10.7 IPS |