Upload Date | September 17 2024 03:48 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT6765G |
System Information | |
---|---|
Operating System | Android 13 |
Model | OPPO CPH2325 |
Model ID | OPPO CPH2325 |
Motherboard | k65v1_64_bsp |
CPU Information | |
---|---|
Name | ARM MT6765G |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3331 revision 4 |
Base Frequency | 2.30 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.30 GHz |
Memory Information | |
---|---|
Size | 3.70 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
99
18.4 IPS |
|
Image Classification (HP)
|
100% |
60
11.2 IPS |
|
Image Classification (Q)
|
100% |
83
15.4 IPS |
|
Image Segmentation (SP)
|
100% |
54
0.87 IPS |
|
Image Segmentation (HP)
|
100% |
125
2.03 IPS |
|
Image Segmentation (Q)
|
98% |
259
4.22 IPS |
|
Pose Estimation (SP)
|
100% |
376
0.44 IPS |
|
Pose Estimation (HP)
|
100% |
310
0.36 IPS |
|
Pose Estimation (Q)
|
84% |
321
0.38 IPS |
|
Object Detection (SP)
|
100% |
128
10.1 IPS |
|
Object Detection (HP)
|
100% |
89
7.06 IPS |
|
Object Detection (Q)
|
83% |
123
9.90 IPS |
|
Face Detection (SP)
|
100% |
199
2.36 IPS |
|
Face Detection (HP)
|
100% |
267
3.17 IPS |
|
Face Detection (Q)
|
95% |
367
4.39 IPS |
|
Depth Estimation (SP)
|
100% |
317
2.44 IPS |
|
Depth Estimation (HP)
|
99% |
235
1.81 IPS |
|
Depth Estimation (Q)
|
64% |
298
2.73 IPS |
|
Style Transfer (SP)
|
89% |
759
0.99 IPS |
|
Style Transfer (HP)
|
89% |
925
1.20 IPS |
|
Style Transfer (Q)
|
98% |
579
0.75 IPS |
|
Image Super-Resolution (SP)
|
100% |
144
5.31 IPS |
|
Image Super-Resolution (HP)
|
100% |
183
6.77 IPS |
|
Image Super-Resolution (Q)
|
97% |
243
9.02 IPS |
|
Text Classification (SP)
|
100% |
102
136.5 IPS |
|
Text Classification (HP)
|
100% |
105
139.8 IPS |
|
Text Classification (Q)
|
88% |
121
163.7 IPS |
|
Machine Translation (SP)
|
100% |
121
2.09 IPS |
|
Machine Translation (HP)
|
100% |
146
2.52 IPS |
|
Machine Translation (Q)
|
50% |
56
2.01 IPS |