Upload Date | July 26 2024 02:42 PM |
Views | 4 |
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% |
622
116.5 IPS |
|
Image Classification (F16)
|
100% |
847
158.5 IPS |
|
Image Classification (I8)
|
99% |
674
126.1 IPS |
|
Image Segmentation (F32)
|
100% |
851
14.2 IPS |
|
Image Segmentation (F16)
|
100% |
1018
17.0 IPS |
|
Image Segmentation (I8)
|
98% |
946
15.8 IPS |
|
Pose Estimation (F32)
|
100% |
931
1.13 IPS |
|
Pose Estimation (F16)
|
100% |
1381
1.67 IPS |
|
Pose Estimation (I8)
|
100% |
1387
1.68 IPS |
|
Object Detection (F32)
|
100% |
456
34.0 IPS |
|
Object Detection (F16)
|
100% |
376
28.0 IPS |
|
Object Detection (I8)
|
62% |
486
36.3 IPS |
|
Face Detection (F32)
|
100% |
2229
26.5 IPS |
|
Face Detection (F16)
|
97% |
2289
27.2 IPS |
|
Face Detection (I8)
|
86% |
3090
36.7 IPS |
|
Depth Estimation (F32)
|
100% |
1418
11.0 IPS |
|
Depth Estimation (F16)
|
100% |
2782
21.6 IPS |
|
Depth Estimation (I8)
|
95% |
2736
21.2 IPS |
|
Style Transfer (F32)
|
100% |
3582
4.71 IPS |
|
Style Transfer (F16)
|
100% |
8101
10.7 IPS |
|
Style Transfer (I8)
|
98% |
8093
10.6 IPS |
|
Image Super-Resolution (F32)
|
100% |
472
16.8 IPS |
|
Image Super-Resolution (F16)
|
100% |
414
14.8 IPS |
|
Image Super-Resolution (I8)
|
98% |
414
14.8 IPS |
|
Text Classification (F32)
|
100% |
305
438.8 IPS |
|
Text Classification (F16)
|
100% |
295
424.2 IPS |
|
Text Classification (I8)
|
92% |
481
691.2 IPS |
|
Machine Translation (F32)
|
100% |
527
9.70 IPS |
|
Machine Translation (F16)
|
100% |
532
9.79 IPS |
|
Machine Translation (I8)
|
64% |
527
9.69 IPS |