Upload Date | November 21 2024 12:18 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | OnePlus PJZ110 |
Model ID | OnePlus PJZ110 |
Motherboard | sun |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 3 part 1 revision 4 |
Base Frequency | 3.53 GHz |
Cluster 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.32 GHz |
Memory Information | |
---|---|
Size | 10.86 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
639
118.8 IPS |
|
Image Classification (HP)
|
100% |
569
105.8 IPS |
|
Image Classification (Q)
|
99% |
845
157.7 IPS |
|
Image Segmentation (SP)
|
100% |
1047
17.0 IPS |
|
Image Segmentation (HP)
|
100% |
1956
31.7 IPS |
|
Image Segmentation (Q)
|
98% |
1158
18.8 IPS |
|
Pose Estimation (SP)
|
100% |
1634
1.91 IPS |
|
Pose Estimation (HP)
|
100% |
2783
3.25 IPS |
|
Pose Estimation (Q)
|
96% |
2777
3.25 IPS |
|
Object Detection (SP)
|
100% |
538
42.7 IPS |
|
Object Detection (HP)
|
100% |
1014
80.4 IPS |
|
Object Detection (Q)
|
86% |
1085
87.2 IPS |
|
Face Detection (SP)
|
100% |
2900
34.5 IPS |
|
Face Detection (HP)
|
100% |
3284
39.0 IPS |
|
Face Detection (Q)
|
97% |
2572
30.7 IPS |
|
Depth Estimation (SP)
|
100% |
1555
12.0 IPS |
|
Depth Estimation (HP)
|
99% |
4541
35.1 IPS |
|
Depth Estimation (Q)
|
63% |
3752
34.9 IPS |
|
Style Transfer (SP)
|
100% |
5759
7.40 IPS |
|
Style Transfer (HP)
|
100% |
12562
16.1 IPS |
|
Style Transfer (Q)
|
98% |
12288
15.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
632
23.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
2110
77.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
2068
76.6 IPS |
|
Text Classification (SP)
|
100% |
221
295.5 IPS |
|
Text Classification (HP)
|
100% |
186
248.0 IPS |
|
Text Classification (Q)
|
91% |
314
422.4 IPS |
|
Machine Translation (SP)
|
100% |
333
5.74 IPS |
|
Machine Translation (HP)
|
100% |
340
5.85 IPS |
|
Machine Translation (Q)
|
57% |
267
6.54 IPS |