Upload Date | April 12 2025 11:44 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | MediaTek Dimensity 8100 Max |
System Information | |
---|---|
Operating System | Android 15 |
Model | OnePlus 10R |
Model ID | OnePlus CPH2411 |
Motherboard | k6895v1_64 |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 4 Cores @ 2.85 GHz |
Memory Information | |
---|---|
Size | 7.23 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
596
110.9 IPS |
|
Image Classification (HP)
|
100% |
584
108.6 IPS |
|
Image Classification (Q)
|
100% |
1789
332.7 IPS |
|
Image Segmentation (SP)
|
100% |
783
12.7 IPS |
|
Image Segmentation (HP)
|
100% |
766
12.4 IPS |
|
Image Segmentation (Q)
|
98% |
2063
33.5 IPS |
|
Pose Estimation (SP)
|
100% |
2772
3.24 IPS |
|
Pose Estimation (HP)
|
100% |
2667
3.11 IPS |
|
Pose Estimation (Q)
|
84% |
4174
4.95 IPS |
|
Object Detection (SP)
|
100% |
558
44.2 IPS |
|
Object Detection (HP)
|
100% |
565
44.8 IPS |
|
Object Detection (Q)
|
83% |
1642
132.6 IPS |
|
Face Detection (SP)
|
100% |
1827
21.7 IPS |
|
Face Detection (HP)
|
100% |
1789
21.3 IPS |
|
Face Detection (Q)
|
95% |
3916
46.8 IPS |
|
Depth Estimation (SP)
|
100% |
2374
18.3 IPS |
|
Depth Estimation (HP)
|
99% |
2336
18.0 IPS |
|
Depth Estimation (Q)
|
64% |
3926
36.0 IPS |
|
Style Transfer (SP)
|
89% |
4664
6.05 IPS |
|
Style Transfer (HP)
|
89% |
4657
6.05 IPS |
|
Style Transfer (Q)
|
98% |
9723
12.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
1333
49.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
1344
49.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
1803
66.8 IPS |
|
Text Classification (SP)
|
100% |
479
639.3 IPS |
|
Text Classification (HP)
|
100% |
450
601.0 IPS |
|
Text Classification (Q)
|
88% |
1189
1.60 KIPS |
|
Machine Translation (SP)
|
100% |
999
17.2 IPS |
|
Machine Translation (HP)
|
100% |
962
16.6 IPS |
|
Machine Translation (Q)
|
50% |
633
22.5 IPS |