Upload Date | November 04 2024 12:20 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT6765G |
System Information | |
---|---|
Operating System | Android 12 |
Model | OPPO CPH2471 |
Model ID | OPPO CPH2471 |
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 | 2.72 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
85
15.8 IPS |
|
Image Classification (HP)
|
100% |
80
15.0 IPS |
|
Image Classification (Q)
|
100% |
120
22.3 IPS |
|
Image Segmentation (SP)
|
100% |
76
1.23 IPS |
|
Image Segmentation (HP)
|
100% |
84
1.37 IPS |
|
Image Segmentation (Q)
|
98% |
195
3.18 IPS |
|
Pose Estimation (SP)
|
100% |
415
0.48 IPS |
|
Pose Estimation (HP)
|
100% |
590
0.69 IPS |
|
Pose Estimation (Q)
|
84% |
473
0.56 IPS |
|
Object Detection (SP)
|
100% |
128
10.1 IPS |
|
Object Detection (HP)
|
100% |
130
10.3 IPS |
|
Object Detection (Q)
|
83% |
188
15.2 IPS |
|
Face Detection (SP)
|
100% |
318
3.78 IPS |
|
Face Detection (HP)
|
100% |
284
3.38 IPS |
|
Face Detection (Q)
|
95% |
511
6.10 IPS |
|
Depth Estimation (SP)
|
100% |
429
3.31 IPS |
|
Depth Estimation (HP)
|
99% |
371
2.86 IPS |
|
Depth Estimation (Q)
|
64% |
476
4.36 IPS |
|
Style Transfer (SP)
|
89% |
1160
1.51 IPS |
|
Style Transfer (HP)
|
89% |
1173
1.52 IPS |
|
Style Transfer (Q)
|
98% |
1172
1.51 IPS |
|
Image Super-Resolution (SP)
|
100% |
202
7.44 IPS |
|
Image Super-Resolution (HP)
|
100% |
198
7.31 IPS |
|
Image Super-Resolution (Q)
|
97% |
267
9.88 IPS |
|
Text Classification (SP)
|
100% |
96
128.5 IPS |
|
Text Classification (HP)
|
100% |
77
102.3 IPS |
|
Text Classification (Q)
|
88% |
119
160.8 IPS |
|
Machine Translation (SP)
|
100% |
179
3.08 IPS |
|
Machine Translation (HP)
|
100% |
179
3.08 IPS |
|
Machine Translation (Q)
|
50% |
73
2.58 IPS |