Upload Date | June 21 2025 07:00 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | OPPO CPH2695 |
Model ID | OPPO CPH2695 |
Motherboard | k6835v2_64 |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 5.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
133
24.7 IPS |
|
Image Classification (HP)
|
100% |
414
76.9 IPS |
|
Image Classification (Q)
|
97% |
21
3.88 IPS |
|
Image Segmentation (SP)
|
100% |
259
4.20 IPS |
|
Image Segmentation (HP)
|
100% |
162
2.62 IPS |
|
Image Segmentation (Q)
|
98% |
25
0.41 IPS |
|
Pose Estimation (SP)
|
100% |
930
1.09 IPS |
|
Pose Estimation (HP)
|
98% |
2144
2.51 IPS |
|
Pose Estimation (Q)
|
70% |
1126
1.44 IPS |
|
Object Detection (SP)
|
100% |
155
12.3 IPS |
|
Object Detection (HP)
|
100% |
119
9.42 IPS |
|
Object Detection (Q)
|
80% |
26
2.10 IPS |
|
Face Detection (SP)
|
28% |
45
8.30 IPS |
|
Face Detection (HP)
|
100% |
300
3.56 IPS |
|
Face Detection (Q)
|
97% |
33
0.40 IPS |
|
Depth Estimation (SP)
|
100% |
375
2.89 IPS |
|
Depth Estimation (HP)
|
99% |
255
1.97 IPS |
|
Depth Estimation (Q)
|
57% |
124
1.35 IPS |
|
Style Transfer (SP)
|
100% |
728
0.94 IPS |
|
Style Transfer (HP)
|
100% |
426
0.55 IPS |
|
Style Transfer (Q)
|
98% |
1703
2.20 IPS |
|
Image Super-Resolution (SP)
|
100% |
366
13.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
858
31.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
432
16.0 IPS |
|
Text Classification (SP)
|
100% |
80
106.3 IPS |
|
Text Classification (HP)
|
100% |
169
226.2 IPS |
|
Text Classification (Q)
|
93% |
68
90.7 IPS |
|
Machine Translation (SP)
|
100% |
212
3.66 IPS |
|
Machine Translation (HP)
|
100% |
287
4.95 IPS |
|
Machine Translation (Q)
|
55% |
98
2.60 IPS |