User | dekurver |
Upload Date | January 12 2025 03:18 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | OnePlus CPH2653 |
Model ID | OnePlus CPH2653 |
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 | 14.75 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
126
23.5 IPS |
|
Image Classification (HP)
|
100% |
126
23.5 IPS |
|
Image Classification (Q)
|
99% |
326
60.7 IPS |
|
Image Segmentation (SP)
|
100% |
166
2.69 IPS |
|
Image Segmentation (HP)
|
100% |
166
2.69 IPS |
|
Image Segmentation (Q)
|
98% |
342
5.56 IPS |
|
Pose Estimation (SP)
|
100% |
228
0.27 IPS |
|
Pose Estimation (HP)
|
100% |
228
0.27 IPS |
|
Pose Estimation (Q)
|
98% |
851
1.00 IPS |
|
Object Detection (SP)
|
100% |
125
9.91 IPS |
|
Object Detection (HP)
|
100% |
127
10.0 IPS |
|
Object Detection (Q)
|
87% |
385
30.9 IPS |
|
Face Detection (SP)
|
100% |
352
4.19 IPS |
|
Face Detection (HP)
|
100% |
354
4.21 IPS |
|
Face Detection (Q)
|
97% |
767
9.15 IPS |
|
Depth Estimation (SP)
|
100% |
299
2.31 IPS |
|
Depth Estimation (HP)
|
99% |
300
2.31 IPS |
|
Depth Estimation (Q)
|
64% |
689
6.25 IPS |
|
Style Transfer (SP)
|
100% |
559
0.72 IPS |
|
Style Transfer (HP)
|
100% |
562
0.72 IPS |
|
Style Transfer (Q)
|
98% |
1517
1.96 IPS |
|
Image Super-Resolution (SP)
|
100% |
148
5.45 IPS |
|
Image Super-Resolution (HP)
|
100% |
144
5.33 IPS |
|
Image Super-Resolution (Q)
|
97% |
512
19.0 IPS |
|
Text Classification (SP)
|
100% |
193
258.2 IPS |
|
Text Classification (HP)
|
100% |
187
249.1 IPS |
|
Text Classification (Q)
|
91% |
313
420.4 IPS |
|
Machine Translation (SP)
|
100% |
335
5.77 IPS |
|
Machine Translation (HP)
|
100% |
338
5.83 IPS |
|
Machine Translation (Q)
|
57% |
264
6.44 IPS |