Upload Date | January 12 2025 05:00 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | OPPO CPH2521 |
Model ID | OPPO CPH2521 |
Motherboard | taro |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.50 GHz |
Cluster 3 | 1 Core @ 3.00 GHz |
Memory Information | |
---|---|
Size | 10.95 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
201
37.4 IPS |
|
Image Classification (HP)
|
100% |
8362
1.56 KIPS |
|
Image Classification (Q)
|
99% |
23560
4.39 KIPS |
|
Image Segmentation (SP)
|
100% |
255
4.13 IPS |
|
Image Segmentation (HP)
|
100% |
6652
107.8 IPS |
|
Image Segmentation (Q)
|
98% |
18938
308.0 IPS |
|
Pose Estimation (SP)
|
100% |
365
0.43 IPS |
|
Pose Estimation (HP)
|
100% |
37753
44.1 IPS |
|
Pose Estimation (Q)
|
94% |
225695
264.6 IPS |
|
Object Detection (SP)
|
100% |
198
15.7 IPS |
|
Object Detection (HP)
|
100% |
7866
624.0 IPS |
|
Object Detection (Q)
|
88% |
12166
974.6 IPS |
|
Face Detection (SP)
|
100% |
536
6.37 IPS |
|
Face Detection (HP)
|
100% |
18489
219.7 IPS |
|
Face Detection (Q)
|
97% |
74654
890.1 IPS |
|
Depth Estimation (SP)
|
100% |
448
3.46 IPS |
|
Depth Estimation (HP)
|
99% |
28345
219.0 IPS |
|
Depth Estimation (Q)
|
64% |
61435
565.6 IPS |
|
Style Transfer (SP)
|
100% |
765
0.98 IPS |
|
Style Transfer (HP)
|
98% |
39897
51.4 IPS |
|
Style Transfer (Q)
|
98% |
227008
292.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
216
7.97 IPS |
|
Image Super-Resolution (HP)
|
100% |
21689
800.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
71792
2.66 KIPS |
|
Text Classification (SP)
|
100% |
278
371.2 IPS |
|
Text Classification (HP)
|
100% |
1896
2.53 KIPS |
|
Text Classification (Q)
|
94% |
4437
5.95 KIPS |
|
Machine Translation (SP)
|
100% |
459
7.90 IPS |
|
Machine Translation (HP)
|
100% |
2147
37.0 IPS |
|
Machine Translation (Q)
|
50% |
1149
39.8 IPS |