Upload Date | August 17 2025 10:42 AM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT6765V/WB |
System Information | |
---|---|
Operating System | Android 13 |
Model | samsung SM-A037F |
Model ID | samsung SM-A037F |
Motherboard | a03s |
CPU Information | |
---|---|
Name | ARM MT6765V/WB |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3331 revision 4 |
Base Frequency | 2.30 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.30 GHz |
Memory Information | |
---|---|
Size | 2.70 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
115
21.4 IPS |
|
Image Classification (HP)
|
100% |
94
17.4 IPS |
|
Image Classification (Q)
|
100% |
151
28.0 IPS |
|
Image Segmentation (SP)
|
100% |
132
2.15 IPS |
|
Image Segmentation (HP)
|
100% |
133
2.15 IPS |
|
Image Segmentation (Q)
|
98% |
221
3.60 IPS |
|
Pose Estimation (SP)
|
100% |
404
0.47 IPS |
|
Pose Estimation (HP)
|
100% |
395
0.46 IPS |
|
Pose Estimation (Q)
|
84% |
274
0.32 IPS |
|
Object Detection (SP)
|
100% |
87
6.86 IPS |
|
Object Detection (HP)
|
100% |
86
6.85 IPS |
|
Object Detection (Q)
|
83% |
124
10.0 IPS |
|
Face Detection (SP)
|
100% |
238
2.82 IPS |
|
Face Detection (HP)
|
100% |
227
2.69 IPS |
|
Face Detection (Q)
|
95% |
356
4.25 IPS |
|
Depth Estimation (SP)
|
100% |
301
2.32 IPS |
|
Depth Estimation (HP)
|
99% |
299
2.31 IPS |
|
Depth Estimation (Q)
|
64% |
276
2.53 IPS |
|
Style Transfer (SP)
|
89% |
701
0.91 IPS |
|
Style Transfer (HP)
|
89% |
698
0.91 IPS |
|
Style Transfer (Q)
|
98% |
647
0.83 IPS |
|
Image Super-Resolution (SP)
|
100% |
134
4.94 IPS |
|
Image Super-Resolution (HP)
|
100% |
138
5.08 IPS |
|
Image Super-Resolution (Q)
|
97% |
162
6.01 IPS |
|
Text Classification (SP)
|
100% |
88
117.7 IPS |
|
Text Classification (HP)
|
100% |
98
131.3 IPS |
|
Text Classification (Q)
|
88% |
93
125.8 IPS |
|
Machine Translation (SP)
|
100% |
129
2.23 IPS |
|
Machine Translation (HP)
|
100% |
129
2.22 IPS |
|
Machine Translation (Q)
|
50% |
62
2.19 IPS |