Upload Date | April 24 2025 04:20 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | MediaTek Dimensity 8020 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Motorola Edge 40 |
Model ID | motorola motorola edge 40 |
Motherboard | lyriq |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 4 Cores @ 2.60 GHz |
Memory Information | |
---|---|
Size | 7.28 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
582
108.1 IPS |
|
Image Classification (HP)
|
100% |
854
158.9 IPS |
|
Image Classification (Q)
|
99% |
1996
372.3 IPS |
|
Image Segmentation (SP)
|
100% |
688
11.2 IPS |
|
Image Segmentation (HP)
|
100% |
671
10.9 IPS |
|
Image Segmentation (Q)
|
98% |
1904
31.0 IPS |
|
Pose Estimation (SP)
|
100% |
4215
4.92 IPS |
|
Pose Estimation (HP)
|
100% |
2020
2.36 IPS |
|
Pose Estimation (Q)
|
95% |
9971
11.7 IPS |
|
Object Detection (SP)
|
100% |
347
27.5 IPS |
|
Object Detection (HP)
|
100% |
50
3.97 IPS |
|
Object Detection (Q)
|
89% |
1530
122.5 IPS |
|
Face Detection (SP)
|
100% |
1864
22.2 IPS |
|
Face Detection (HP)
|
100% |
152
1.81 IPS |
|
Face Detection (Q)
|
97% |
5133
61.2 IPS |
|
Depth Estimation (SP)
|
100% |
297
2.29 IPS |
|
Depth Estimation (HP)
|
99% |
116
0.90 IPS |
|
Depth Estimation (Q)
|
64% |
2184
20.1 IPS |
|
Style Transfer (SP)
|
100% |
1456
1.87 IPS |
|
Style Transfer (HP)
|
100% |
216
0.28 IPS |
|
Style Transfer (Q)
|
98% |
2315
2.98 IPS |
|
Image Super-Resolution (SP)
|
100% |
1430
52.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
1543
57.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
4721
174.9 IPS |
|
Text Classification (SP)
|
100% |
111
147.9 IPS |
|
Text Classification (HP)
|
100% |
71
95.4 IPS |
|
Text Classification (Q)
|
92% |
87
116.2 IPS |
|
Machine Translation (SP)
|
100% |
130
2.24 IPS |
|
Machine Translation (HP)
|
100% |
120
2.07 IPS |
|
Machine Translation (Q)
|
55% |
86
2.26 IPS |