Upload Date | December 28 2024 10:28 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | OPPO CPH2519 |
Model ID | OPPO CPH2519 |
Motherboard | k6985v1_64 |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.85 GHz |
Cluster 3 | 1 Core @ 3.05 GHz |
Memory Information | |
---|---|
Size | 11.10 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
285
53.0 IPS |
|
Image Classification (HP)
|
100% |
295
54.8 IPS |
|
Image Classification (Q)
|
99% |
351
65.4 IPS |
|
Image Segmentation (SP)
|
100% |
786
12.7 IPS |
|
Image Segmentation (HP)
|
100% |
879
14.2 IPS |
|
Image Segmentation (Q)
|
98% |
818
13.3 IPS |
|
Pose Estimation (SP)
|
100% |
534
0.62 IPS |
|
Pose Estimation (HP)
|
100% |
735
0.86 IPS |
|
Pose Estimation (Q)
|
96% |
729
0.85 IPS |
|
Object Detection (SP)
|
100% |
264
21.0 IPS |
|
Object Detection (HP)
|
100% |
331
26.2 IPS |
|
Object Detection (Q)
|
83% |
389
31.5 IPS |
|
Face Detection (SP)
|
100% |
1377
16.4 IPS |
|
Face Detection (HP)
|
100% |
1389
16.5 IPS |
|
Face Detection (Q)
|
97% |
1303
15.5 IPS |
|
Depth Estimation (SP)
|
100% |
920
7.09 IPS |
|
Depth Estimation (HP)
|
99% |
1095
8.43 IPS |
|
Depth Estimation (Q)
|
62% |
895
8.47 IPS |
|
Style Transfer (SP)
|
100% |
2639
3.39 IPS |
|
Style Transfer (HP)
|
100% |
3329
4.28 IPS |
|
Style Transfer (Q)
|
98% |
3299
4.25 IPS |
|
Image Super-Resolution (SP)
|
100% |
444
16.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
539
19.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
722
26.8 IPS |
|
Text Classification (SP)
|
100% |
251
334.6 IPS |
|
Text Classification (HP)
|
100% |
238
317.1 IPS |
|
Text Classification (Q)
|
91% |
352
472.7 IPS |
|
Machine Translation (SP)
|
100% |
357
6.15 IPS |
|
Machine Translation (HP)
|
100% |
349
6.00 IPS |
|
Machine Translation (Q)
|
57% |
262
6.39 IPS |