User | zlocorp |
Upload Date | October 04 2024 07:28 AM |
Views | 7 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT6877V/TTZA |
System Information | |
---|---|
Operating System | Android 14 |
Model | realme RMX3741 |
Model ID | realme RMX3741 |
Motherboard | RM6877 |
CPU Information | |
---|---|
Name | ARM MT6877V/TTZA |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.60 GHz |
Memory Information | |
---|---|
Size | 11.28 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
253
47.0 IPS |
|
Image Classification (HP)
|
100% |
251
46.7 IPS |
|
Image Classification (Q)
|
100% |
772
143.5 IPS |
|
Image Segmentation (SP)
|
100% |
323
5.23 IPS |
|
Image Segmentation (HP)
|
100% |
315
5.10 IPS |
|
Image Segmentation (Q)
|
98% |
860
14.0 IPS |
|
Pose Estimation (SP)
|
100% |
1121
1.31 IPS |
|
Pose Estimation (HP)
|
100% |
1138
1.33 IPS |
|
Pose Estimation (Q)
|
84% |
1969
2.33 IPS |
|
Object Detection (SP)
|
100% |
244
19.3 IPS |
|
Object Detection (HP)
|
100% |
213
16.9 IPS |
|
Object Detection (Q)
|
83% |
735
59.4 IPS |
|
Face Detection (SP)
|
100% |
788
9.36 IPS |
|
Face Detection (HP)
|
100% |
797
9.47 IPS |
|
Face Detection (Q)
|
95% |
1566
18.7 IPS |
|
Depth Estimation (SP)
|
100% |
947
7.30 IPS |
|
Depth Estimation (HP)
|
99% |
1074
8.28 IPS |
|
Depth Estimation (Q)
|
64% |
1816
16.6 IPS |
|
Style Transfer (SP)
|
89% |
2118
2.75 IPS |
|
Style Transfer (HP)
|
89% |
2098
2.72 IPS |
|
Style Transfer (Q)
|
98% |
4583
5.91 IPS |
|
Image Super-Resolution (SP)
|
100% |
586
21.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
582
21.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
1091
40.4 IPS |
|
Text Classification (SP)
|
100% |
323
431.8 IPS |
|
Text Classification (HP)
|
100% |
313
418.2 IPS |
|
Text Classification (Q)
|
88% |
732
987.4 IPS |
|
Machine Translation (SP)
|
100% |
482
8.31 IPS |
|
Machine Translation (HP)
|
100% |
480
8.27 IPS |
|
Machine Translation (Q)
|
50% |
403
14.3 IPS |