Upload Date | July 26 2024 02:39 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 | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
472
88.3 IPS |
|
Image Classification (F16)
|
100% |
478
89.5 IPS |
|
Image Classification (I8)
|
97% |
956
178.9 IPS |
|
Image Segmentation (F32)
|
100% |
621
10.4 IPS |
|
Image Segmentation (F16)
|
100% |
597
9.98 IPS |
|
Image Segmentation (I8)
|
98% |
757
12.7 IPS |
|
Pose Estimation (F32)
|
100% |
1170
1.42 IPS |
|
Pose Estimation (F16)
|
100% |
1139
1.38 IPS |
|
Pose Estimation (I8)
|
100% |
4528
5.48 IPS |
|
Object Detection (F32)
|
100% |
494
36.9 IPS |
|
Object Detection (F16)
|
100% |
469
35.0 IPS |
|
Object Detection (I8)
|
61% |
989
73.8 IPS |
|
Face Detection (F32)
|
100% |
1070
12.7 IPS |
|
Face Detection (F16)
|
100% |
1025
12.2 IPS |
|
Face Detection (I8)
|
86% |
1853
22.0 IPS |
|
Depth Estimation (F32)
|
100% |
1052
8.16 IPS |
|
Depth Estimation (F16)
|
100% |
1071
8.30 IPS |
|
Depth Estimation (I8)
|
95% |
2131
16.5 IPS |
|
Style Transfer (F32)
|
100% |
2080
2.74 IPS |
|
Style Transfer (F16)
|
100% |
2046
2.69 IPS |
|
Style Transfer (I8)
|
98% |
5232
6.88 IPS |
|
Image Super-Resolution (F32)
|
100% |
713
25.4 IPS |
|
Image Super-Resolution (F16)
|
100% |
637
22.8 IPS |
|
Image Super-Resolution (I8)
|
98% |
1808
64.6 IPS |
|
Text Classification (F32)
|
100% |
512
735.5 IPS |
|
Text Classification (F16)
|
100% |
519
745.6 IPS |
|
Text Classification (I8)
|
92% |
366
525.7 IPS |
|
Machine Translation (F32)
|
100% |
1061
19.5 IPS |
|
Machine Translation (F16)
|
100% |
1026
18.9 IPS |
|
Machine Translation (I8)
|
64% |
669
12.3 IPS |